---
_id: '14182'
abstract:
- lang: eng
text: "When machine learning systems meet real world applications, accuracy is only\r\none
of several requirements. In this paper, we assay a complementary\r\nperspective
originating from the increasing availability of pre-trained and\r\nregularly improving
state-of-the-art models. While new improved models develop\r\nat a fast pace,
downstream tasks vary more slowly or stay constant. Assume that\r\nwe have a large
unlabelled data set for which we want to maintain accurate\r\npredictions. Whenever
a new and presumably better ML models becomes available,\r\nwe encounter two problems:
(i) given a limited budget, which data points should\r\nbe re-evaluated using
the new model?; and (ii) if the new predictions differ\r\nfrom the current ones,
should we update? Problem (i) is about compute cost,\r\nwhich matters for very
large data sets and models. Problem (ii) is about\r\nmaintaining consistency of
the predictions, which can be highly relevant for\r\ndownstream applications;
our demand is to avoid negative flips, i.e., changing\r\ncorrect to incorrect
predictions. In this paper, we formalize the Prediction\r\nUpdate Problem and
present an efficient probabilistic approach as answer to the\r\nabove questions.
In extensive experiments on standard classification benchmark\r\ndata sets, we
show that our method outperforms alternative strategies along key\r\nmetrics for
backward-compatible prediction updates."
article_processing_charge: No
arxiv: 1
author:
- first_name: Frederik
full_name: Träuble, Frederik
last_name: Träuble
- first_name: Julius von
full_name: Kügelgen, Julius von
last_name: Kügelgen
- first_name: Matthäus
full_name: Kleindessner, Matthäus
last_name: Kleindessner
- first_name: Francesco
full_name: Locatello, Francesco
id: 26cfd52f-2483-11ee-8040-88983bcc06d4
last_name: Locatello
orcid: 0000-0002-4850-0683
- first_name: Bernhard
full_name: Schölkopf, Bernhard
last_name: Schölkopf
- first_name: Peter
full_name: Gehler, Peter
last_name: Gehler
citation:
ama: 'Träuble F, Kügelgen J von, Kleindessner M, Locatello F, Schölkopf B, Gehler
P. Backward-compatible prediction updates: A probabilistic approach. In: 35th
Conference on Neural Information Processing Systems. Vol 34. ; 2021:116-128.'
apa: 'Träuble, F., Kügelgen, J. von, Kleindessner, M., Locatello, F., Schölkopf,
B., & Gehler, P. (2021). Backward-compatible prediction updates: A probabilistic
approach. In 35th Conference on Neural Information Processing Systems (Vol.
34, pp. 116–128). Virtual.'
chicago: 'Träuble, Frederik, Julius von Kügelgen, Matthäus Kleindessner, Francesco
Locatello, Bernhard Schölkopf, and Peter Gehler. “Backward-Compatible Prediction
Updates: A Probabilistic Approach.” In 35th Conference on Neural Information
Processing Systems, 34:116–28, 2021.'
ieee: 'F. Träuble, J. von Kügelgen, M. Kleindessner, F. Locatello, B. Schölkopf,
and P. Gehler, “Backward-compatible prediction updates: A probabilistic approach,”
in 35th Conference on Neural Information Processing Systems, Virtual, 2021,
vol. 34, pp. 116–128.'
ista: 'Träuble F, Kügelgen J von, Kleindessner M, Locatello F, Schölkopf B, Gehler
P. 2021. Backward-compatible prediction updates: A probabilistic approach. 35th
Conference on Neural Information Processing Systems. NeurIPS: Neural Information
Processing Systems vol. 34, 116–128.'
mla: 'Träuble, Frederik, et al. “Backward-Compatible Prediction Updates: A Probabilistic
Approach.” 35th Conference on Neural Information Processing Systems, vol.
34, 2021, pp. 116–28.'
short: F. Träuble, J. von Kügelgen, M. Kleindessner, F. Locatello, B. Schölkopf,
P. Gehler, in:, 35th Conference on Neural Information Processing Systems, 2021,
pp. 116–128.
conference:
end_date: 2021-12-10
location: Virtual
name: 'NeurIPS: Neural Information Processing Systems'
start_date: 2021-12-07
date_created: 2023-08-22T14:05:41Z
date_published: 2021-07-02T00:00:00Z
date_updated: 2023-09-11T11:31:59Z
day: '02'
department:
- _id: FrLo
extern: '1'
external_id:
arxiv:
- '2107.01057'
intvolume: ' 34'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/abs/2107.01057
month: '07'
oa: 1
oa_version: Preprint
page: 116-128
publication: 35th Conference on Neural Information Processing Systems
publication_identifier:
isbn:
- '9781713845393'
publication_status: published
quality_controlled: '1'
status: public
title: 'Backward-compatible prediction updates: A probabilistic approach'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 34
year: '2021'
...
---
OA_place: repository
_id: '14185'
abstract:
- lang: eng
text: A method involves receiving a perceptual representation including a plurality
of feature vectors, and initializing a plurality of slot vectors represented by
a neural network memory unit. Each respective slot vector is configured to represent
a corresponding entity in the perceptual representation. The method also involves
determining an attention matrix based on a product of the plurality of feature
vectors transformed by a key function and the plurality of slot vectors transformed
by a query function. Each respective value of a plurality of values along each
respective dimension of the attention matrix is normalized with respect to the
plurality of values. The method additionally involves determining an update matrix
based on the plurality of feature vectors transformed by a value function and
the attention matrix, and updating the plurality of slot vectors based on the
update matrix by way of the neural network memory unit.
applicant:
- Google LLC
application_date: 2020-07-13
application_number: '16 / 927,018 '
article_processing_charge: No
arxiv: 1
author:
- first_name: Dirk
full_name: Weissenborn, Dirk
last_name: Weissenborn
- first_name: Jakob
full_name: Uszkoreit, Jakob
last_name: Uszkoreit
- first_name: Thomas
full_name: Unterthiner, Thomas
last_name: Unterthiner
- first_name: Aravindh
full_name: Mahendran, Aravindh
last_name: Mahendran
- first_name: Francesco
full_name: Locatello, Francesco
id: 26cfd52f-2483-11ee-8040-88983bcc06d4
last_name: Locatello
orcid: 0000-0002-4850-0683
- first_name: Thomas
full_name: Kipf, Thomas
last_name: Kipf
- first_name: Georg
full_name: Heigold, Georg
last_name: Heigold
- first_name: Alexey
full_name: Dosovitskiy, Alexey
last_name: Dosovitskiy
citation:
ama: Weissenborn D, Uszkoreit J, Unterthiner T, et al. Object-centric learning with
slot attention. 2021.
apa: Weissenborn, D., Uszkoreit, J., Unterthiner, T., Mahendran, A., Locatello,
F., Kipf, T., … Dosovitskiy, A. (2021). Object-centric learning with slot attention.
chicago: Weissenborn, Dirk, Jakob Uszkoreit, Thomas Unterthiner, Aravindh Mahendran,
Francesco Locatello, Thomas Kipf, Georg Heigold, and Alexey Dosovitskiy. “Object-Centric
Learning with Slot Attention,” 2021.
ieee: D. Weissenborn et al., “Object-centric learning with slot attention.”
2021.
ista: Weissenborn D, Uszkoreit J, Unterthiner T, Mahendran A, Locatello F, Kipf
T, Heigold G, Dosovitskiy A. 2021. Object-centric learning with slot attention.
mla: Weissenborn, Dirk, et al. Object-Centric Learning with Slot Attention.
2021.
short: D. Weissenborn, J. Uszkoreit, T. Unterthiner, A. Mahendran, F. Locatello,
T. Kipf, G. Heigold, A. Dosovitskiy, (2021).
date_created: 2023-08-22T14:07:06Z
date_published: 2021-12-09T00:00:00Z
date_updated: 2025-01-31T11:35:46Z
day: '09'
department:
- _id: FrLo
extern: '1'
external_id:
arxiv:
- '2006.15055'
ipc: G06N 3/063 ; G06N 3/08 ; G06F 17/16
ipn: US20210383199A1
main_file_link:
- open_access: '1'
url: https://patents.google.com/patent/US20210383199A1/en
month: '12'
oa: 1
oa_version: Published Version
publication_date: 2021-12-09
status: public
title: Object-centric learning with slot attention
type: patent
user_id: 8b945eb4-e2f2-11eb-945a-df72226e66a9
year: '2021'
...
---
_id: '14221'
abstract:
- lang: eng
text: 'The world is structured in countless ways. It may be prudent to enforce corresponding
structural properties to a learning algorithm''s solution, such as incorporating
prior beliefs, natural constraints, or causal structures. Doing so may translate
to faster, more accurate, and more flexible models, which may directly relate
to real-world impact. In this dissertation, we consider two different research
areas that concern structuring a learning algorithm''s solution: when the structure
is known and when it has to be discovered.'
article_number: '2111.13693'
article_processing_charge: No
arxiv: 1
author:
- first_name: Francesco
full_name: Locatello, Francesco
id: 26cfd52f-2483-11ee-8040-88983bcc06d4
last_name: Locatello
orcid: 0000-0002-4850-0683
citation:
ama: Locatello F. Enforcing and discovering structure in machine learning. arXiv.
doi:10.48550/arXiv.2111.13693
apa: Locatello, F. (n.d.). Enforcing and discovering structure in machine learning.
arXiv. https://doi.org/10.48550/arXiv.2111.13693
chicago: Locatello, Francesco. “Enforcing and Discovering Structure in Machine Learning.”
ArXiv, n.d. https://doi.org/10.48550/arXiv.2111.13693.
ieee: F. Locatello, “Enforcing and discovering structure in machine learning,” arXiv.
.
ista: Locatello F. Enforcing and discovering structure in machine learning. arXiv,
2111.13693.
mla: Locatello, Francesco. “Enforcing and Discovering Structure in Machine Learning.”
ArXiv, 2111.13693, doi:10.48550/arXiv.2111.13693.
short: F. Locatello, ArXiv (n.d.).
date_created: 2023-08-22T14:23:35Z
date_published: 2021-11-26T00:00:00Z
date_updated: 2024-10-14T12:27:49Z
day: '26'
department:
- _id: FrLo
doi: 10.48550/arXiv.2111.13693
extern: '1'
external_id:
arxiv:
- '2111.13693'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.2111.13693
month: '11'
oa: 1
oa_version: Preprint
publication: arXiv
publication_status: submitted
status: public
title: Enforcing and discovering structure in machine learning
type: preprint
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2021'
...
---
_id: '14332'
abstract:
- lang: eng
text: Learning data representations that are useful for various downstream tasks
is a cornerstone of artificial intelligence. While existing methods are typically
evaluated on downstream tasks such as classification or generative image quality,
we propose to assess representations through their usefulness in downstream control
tasks, such as reaching or pushing objects. By training over 10,000 reinforcement
learning policies, we extensively evaluate to what extent different representation
properties affect out-of-distribution (OOD) generalization. Finally, we demonstrate
zero-shot transfer of these policies from simulation to the real world, without
any domain randomization or fine-tuning. This paper aims to establish the first
systematic characterization of the usefulness of learned representations for real-world
OOD downstream tasks.
article_processing_charge: No
author:
- first_name: Frederik
full_name: Träuble, Frederik
last_name: Träuble
- first_name: Andrea
full_name: Dittadi, Andrea
last_name: Dittadi
- first_name: Manuel
full_name: Wuthrich, Manuel
last_name: Wuthrich
- first_name: Felix
full_name: Widmaier, Felix
last_name: Widmaier
- first_name: Peter Vincent
full_name: Gehler, Peter Vincent
last_name: Gehler
- first_name: Ole
full_name: Winther, Ole
last_name: Winther
- first_name: Francesco
full_name: Locatello, Francesco
id: 26cfd52f-2483-11ee-8040-88983bcc06d4
last_name: Locatello
orcid: 0000-0002-4850-0683
- first_name: Olivier
full_name: Bachem, Olivier
last_name: Bachem
- first_name: Bernhard
full_name: Schölkopf, Bernhard
last_name: Schölkopf
- first_name: Stefan
full_name: Bauer, Stefan
last_name: Bauer
citation:
ama: 'Träuble F, Dittadi A, Wuthrich M, et al. Representation learning for out-of-distribution
generalization in reinforcement learning. In: ICML 2021 Workshop on Unsupervised
Reinforcement Learning. ; 2021.'
apa: Träuble, F., Dittadi, A., Wuthrich, M., Widmaier, F., Gehler, P. V., Winther,
O., … Bauer, S. (2021). Representation learning for out-of-distribution generalization
in reinforcement learning. In ICML 2021 Workshop on Unsupervised Reinforcement
Learning. Virtual.
chicago: Träuble, Frederik, Andrea Dittadi, Manuel Wuthrich, Felix Widmaier, Peter
Vincent Gehler, Ole Winther, Francesco Locatello, Olivier Bachem, Bernhard Schölkopf,
and Stefan Bauer. “Representation Learning for Out-of-Distribution Generalization
in Reinforcement Learning.” In ICML 2021 Workshop on Unsupervised Reinforcement
Learning, 2021.
ieee: F. Träuble et al., “Representation learning for out-of-distribution
generalization in reinforcement learning,” in ICML 2021 Workshop on Unsupervised
Reinforcement Learning, Virtual, 2021.
ista: 'Träuble F, Dittadi A, Wuthrich M, Widmaier F, Gehler PV, Winther O, Locatello
F, Bachem O, Schölkopf B, Bauer S. 2021. Representation learning for out-of-distribution
generalization in reinforcement learning. ICML 2021 Workshop on Unsupervised Reinforcement
Learning. ICML: International Conference on Machine Learning.'
mla: Träuble, Frederik, et al. “Representation Learning for Out-of-Distribution
Generalization in Reinforcement Learning.” ICML 2021 Workshop on Unsupervised
Reinforcement Learning, 2021.
short: F. Träuble, A. Dittadi, M. Wuthrich, F. Widmaier, P.V. Gehler, O. Winther,
F. Locatello, O. Bachem, B. Schölkopf, S. Bauer, in:, ICML 2021 Workshop on Unsupervised
Reinforcement Learning, 2021.
conference:
end_date: 2021-07-23
location: Virtual
name: 'ICML: International Conference on Machine Learning'
start_date: 2021-07-23
date_created: 2023-09-13T12:43:14Z
date_published: 2021-07-23T00:00:00Z
date_updated: 2023-09-13T12:44:00Z
day: '23'
department:
- _id: FrLo
extern: '1'
language:
- iso: eng
month: '07'
oa_version: None
publication: ICML 2021 Workshop on Unsupervised Reinforcement Learning
publication_status: published
quality_controlled: '1'
status: public
title: Representation learning for out-of-distribution generalization in reinforcement
learning
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2021'
...
---
OA_type: closed access
_id: '17876'
abstract:
- lang: eng
text: The scanning tunneling microscope-based break-junction (STM-BJ) technique
is the most common method used to study the electronic properties of single-molecule
junctions. It relies on repeatedly forming and rupturing a Au contact in an environment
of the target molecules. The probability of junction formation is typically very
high (∼70–95%), prompting questions relating to how the nanoscale structure of
the Au electrode before the metal point contact ruptures alters junction formation.
Here we analyze conductance traces measured with the STM-BJ setup by combining
correlation analysis and multiple machine learning tools, including gradient-boosted
trees and neural networks. We show that two key features describing the Au–Au
contact prior to rupture determine the extent of contact relaxation (snapback)
and the probability of junction formation. Importantly, our data strongly indicate
that molecular junctions are formed prior to the rupture of the Au–Au contact,
explaining the high probability of junction formation observed in room-temperature
solution measurements.
article_processing_charge: No
article_type: original
author:
- first_name: Tianren
full_name: Fu, Tianren
last_name: Fu
- first_name: Kathleen
full_name: Frommer, Kathleen
last_name: Frommer
- first_name: Colin
full_name: Nuckolls, Colin
last_name: Nuckolls
- first_name: Latha
full_name: Venkataraman, Latha
id: 9ebb78a5-cc0d-11ee-8322-fae086a32caf
last_name: Venkataraman
orcid: 0000-0002-6957-6089
citation:
ama: Fu T, Frommer K, Nuckolls C, Venkataraman L. Single-molecule junction formation
in break-junction measurements. The Journal of Physical Chemistry Letters.
2021;12(44):10802-10807. doi:10.1021/acs.jpclett.1c03160
apa: Fu, T., Frommer, K., Nuckolls, C., & Venkataraman, L. (2021). Single-molecule
junction formation in break-junction measurements. The Journal of Physical
Chemistry Letters. American Chemical Society. https://doi.org/10.1021/acs.jpclett.1c03160
chicago: Fu, Tianren, Kathleen Frommer, Colin Nuckolls, and Latha Venkataraman.
“Single-Molecule Junction Formation in Break-Junction Measurements.” The Journal
of Physical Chemistry Letters. American Chemical Society, 2021. https://doi.org/10.1021/acs.jpclett.1c03160.
ieee: T. Fu, K. Frommer, C. Nuckolls, and L. Venkataraman, “Single-molecule junction
formation in break-junction measurements,” The Journal of Physical Chemistry
Letters, vol. 12, no. 44. American Chemical Society, pp. 10802–10807, 2021.
ista: Fu T, Frommer K, Nuckolls C, Venkataraman L. 2021. Single-molecule junction
formation in break-junction measurements. The Journal of Physical Chemistry Letters.
12(44), 10802–10807.
mla: Fu, Tianren, et al. “Single-Molecule Junction Formation in Break-Junction Measurements.”
The Journal of Physical Chemistry Letters, vol. 12, no. 44, American Chemical
Society, 2021, pp. 10802–07, doi:10.1021/acs.jpclett.1c03160.
short: T. Fu, K. Frommer, C. Nuckolls, L. Venkataraman, The Journal of Physical
Chemistry Letters 12 (2021) 10802–10807.
date_created: 2024-09-06T13:10:30Z
date_published: 2021-11-01T00:00:00Z
date_updated: 2024-12-10T10:03:05Z
day: '01'
doi: 10.1021/acs.jpclett.1c03160
extern: '1'
external_id:
pmid:
- '34723548'
intvolume: ' 12'
issue: '44'
language:
- iso: eng
month: '11'
oa_version: None
page: 10802-10807
pmid: 1
publication: The Journal of Physical Chemistry Letters
publication_identifier:
issn:
- 1948-7185
publication_status: published
publisher: American Chemical Society
quality_controlled: '1'
scopus_import: '1'
status: public
title: Single-molecule junction formation in break-junction measurements
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 12
year: '2021'
...
---
OA_type: closed access
_id: '17877'
abstract:
- lang: eng
text: Chemical reactions that occur at nanostructured electrodes have garnered widespread
interest because of their potential applications in fields including nanotechnology,
green chemistry and fundamental physical organic chemistry. Much of our present
understanding of these reactions comes from probes that interrogate ensembles
of molecules undergoing various stages of the transformation concurrently. Exquisite
control over single-molecule reactivity lets us construct new molecules and further
our understanding of nanoscale chemical phenomena. We can study single molecules
using instruments such as the scanning tunnelling microscope, which can additionally
be part of a mechanically controlled break junction. These are unique tools that
can offer a high level of detail. They probe the electronic conductance of individual
molecules and catalyse chemical reactions by establishing environments with reactive
metal sites on nanoscale electrodes. This Review describes how chemical reactions
involving bond cleavage and formation can be triggered at nanoscale electrodes
and studied one molecule at a time.
article_processing_charge: No
article_type: review
author:
- first_name: Ilana
full_name: Stone, Ilana
last_name: Stone
- first_name: Rachel L.
full_name: Starr, Rachel L.
last_name: Starr
- first_name: Yaping
full_name: Zang, Yaping
last_name: Zang
- first_name: Colin
full_name: Nuckolls, Colin
last_name: Nuckolls
- first_name: Michael L.
full_name: Steigerwald, Michael L.
last_name: Steigerwald
- first_name: Tristan H.
full_name: Lambert, Tristan H.
last_name: Lambert
- first_name: Xavier
full_name: Roy, Xavier
last_name: Roy
- first_name: Latha
full_name: Venkataraman, Latha
id: 9ebb78a5-cc0d-11ee-8322-fae086a32caf
last_name: Venkataraman
orcid: 0000-0002-6957-6089
citation:
ama: Stone I, Starr RL, Zang Y, et al. A single-molecule blueprint for synthesis.
Nature Reviews Chemistry. 2021;5(10):695-710. doi:10.1038/s41570-021-00316-y
apa: Stone, I., Starr, R. L., Zang, Y., Nuckolls, C., Steigerwald, M. L., Lambert,
T. H., … Venkataraman, L. (2021). A single-molecule blueprint for synthesis. Nature
Reviews Chemistry. Springer Nature. https://doi.org/10.1038/s41570-021-00316-y
chicago: Stone, Ilana, Rachel L. Starr, Yaping Zang, Colin Nuckolls, Michael L.
Steigerwald, Tristan H. Lambert, Xavier Roy, and Latha Venkataraman. “A Single-Molecule
Blueprint for Synthesis.” Nature Reviews Chemistry. Springer Nature, 2021.
https://doi.org/10.1038/s41570-021-00316-y.
ieee: I. Stone et al., “A single-molecule blueprint for synthesis,” Nature
Reviews Chemistry, vol. 5, no. 10. Springer Nature, pp. 695–710, 2021.
ista: Stone I, Starr RL, Zang Y, Nuckolls C, Steigerwald ML, Lambert TH, Roy X,
Venkataraman L. 2021. A single-molecule blueprint for synthesis. Nature Reviews
Chemistry. 5(10), 695–710.
mla: Stone, Ilana, et al. “A Single-Molecule Blueprint for Synthesis.” Nature
Reviews Chemistry, vol. 5, no. 10, Springer Nature, 2021, pp. 695–710, doi:10.1038/s41570-021-00316-y.
short: I. Stone, R.L. Starr, Y. Zang, C. Nuckolls, M.L. Steigerwald, T.H. Lambert,
X. Roy, L. Venkataraman, Nature Reviews Chemistry 5 (2021) 695–710.
date_created: 2024-09-06T13:11:31Z
date_published: 2021-08-25T00:00:00Z
date_updated: 2024-12-10T10:05:51Z
day: '25'
doi: 10.1038/s41570-021-00316-y
extern: '1'
external_id:
pmid:
- '37118183'
intvolume: ' 5'
issue: '10'
language:
- iso: eng
month: '08'
oa_version: None
page: 695-710
pmid: 1
publication: Nature Reviews Chemistry
publication_identifier:
issn:
- 2397-3358
publication_status: published
publisher: Springer Nature
quality_controlled: '1'
scopus_import: '1'
status: public
title: A single-molecule blueprint for synthesis
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 5
year: '2021'
...
---
DOAJ_listed: '1'
OA_place: publisher
OA_type: gold
_id: '17899'
abstract:
- lang: eng
text: Designing highly insulating sub-nanometer molecules is difficult because tunneling
conductance increases exponentially with decreasing molecular length. This challenge
is further enhanced by the fact that most molecules cannot achieve full conductance
suppression with destructive quantum interference. Here, we present results for
a series of small saturated heterocyclic alkanes where we show that conductance
is suppressed due to destructive interference. Using the STM-BJ technique and
density functional theory calculations, we confirm that their single-molecule
junction conductance is lower than analogous alkanes of similar length. We rationalize
the suppression of conductance in the junctions through analysis of the computed
ballistic current density. We find there are highly symmetric ring currents, which
reverse direction at the antiresonance in the Landauer transmission near the Fermi
energy. This pattern has not been seen in earlier studies of larger bicyclic systems
exhibiting interference effects and constitutes clear-cut evidence of destructive
σ-interference. The finding of heterocyclic alkanes with destructive quantum interference
charts a pathway for chemical design of short molecular insulators using organic
molecules.
article_processing_charge: Yes
article_type: original
author:
- first_name: Boyuan
full_name: Zhang, Boyuan
last_name: Zhang
- first_name: Marc H.
full_name: Garner, Marc H.
last_name: Garner
- first_name: Liang
full_name: Li, Liang
last_name: Li
- first_name: Luis M.
full_name: Campos, Luis M.
last_name: Campos
- first_name: Gemma C.
full_name: Solomon, Gemma C.
last_name: Solomon
- first_name: Latha
full_name: Venkataraman, Latha
id: 9ebb78a5-cc0d-11ee-8322-fae086a32caf
last_name: Venkataraman
orcid: 0000-0002-6957-6089
citation:
ama: 'Zhang B, Garner MH, Li L, Campos LM, Solomon GC, Venkataraman L. Destructive
quantum interference in heterocyclic alkanes: The search for ultra-short molecular
insulators. Chemical Science. 2021;12(30):10299-10305. doi:10.1039/d1sc02287c'
apa: 'Zhang, B., Garner, M. H., Li, L., Campos, L. M., Solomon, G. C., & Venkataraman,
L. (2021). Destructive quantum interference in heterocyclic alkanes: The search
for ultra-short molecular insulators. Chemical Science. Royal Society of
Chemistry. https://doi.org/10.1039/d1sc02287c'
chicago: 'Zhang, Boyuan, Marc H. Garner, Liang Li, Luis M. Campos, Gemma C. Solomon,
and Latha Venkataraman. “Destructive Quantum Interference in Heterocyclic Alkanes:
The Search for Ultra-Short Molecular Insulators.” Chemical Science. Royal
Society of Chemistry, 2021. https://doi.org/10.1039/d1sc02287c.'
ieee: 'B. Zhang, M. H. Garner, L. Li, L. M. Campos, G. C. Solomon, and L. Venkataraman,
“Destructive quantum interference in heterocyclic alkanes: The search for ultra-short
molecular insulators,” Chemical Science, vol. 12, no. 30. Royal Society
of Chemistry, pp. 10299–10305, 2021.'
ista: 'Zhang B, Garner MH, Li L, Campos LM, Solomon GC, Venkataraman L. 2021. Destructive
quantum interference in heterocyclic alkanes: The search for ultra-short molecular
insulators. Chemical Science. 12(30), 10299–10305.'
mla: 'Zhang, Boyuan, et al. “Destructive Quantum Interference in Heterocyclic Alkanes:
The Search for Ultra-Short Molecular Insulators.” Chemical Science, vol.
12, no. 30, Royal Society of Chemistry, 2021, pp. 10299–305, doi:10.1039/d1sc02287c.'
short: B. Zhang, M.H. Garner, L. Li, L.M. Campos, G.C. Solomon, L. Venkataraman,
Chemical Science 12 (2021) 10299–10305.
date_created: 2024-09-09T06:42:54Z
date_published: 2021-06-30T00:00:00Z
date_updated: 2024-12-10T10:11:16Z
day: '30'
doi: 10.1039/d1sc02287c
extern: '1'
external_id:
pmid:
- '34476051'
intvolume: ' 12'
issue: '30'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.1039/D1SC02287C
month: '06'
oa: 1
oa_version: Published Version
page: 10299-10305
pmid: 1
publication: Chemical Science
publication_identifier:
eissn:
- 2041-6539
issn:
- 2041-6520
publication_status: published
publisher: Royal Society of Chemistry
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Destructive quantum interference in heterocyclic alkanes: The search for ultra-short
molecular insulators'
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 12
year: '2021'
...
---
OA_type: closed access
_id: '17900'
abstract:
- lang: eng
text: To rival the performance of modern integrated circuits, single-molecule devices
must be designed to exhibit extremely nonlinear current–voltage (I–V) characteristics1,2,3,4.
A common approach is to design molecular backbones where destructive quantum interference
(QI) between the highest occupied molecular orbital (HOMO) and the lowest unoccupied
molecular orbital (LUMO) produces a nonlinear energy-dependent tunnelling probability
near the electrode Fermi energy (EF)5,6,7,8. However, tuning such systems is not
straightforward, as aligning the frontier orbitals to EF is hard to control9.
Here, we instead create a molecular system where constructive QI between the HOMO
and LUMO is suppressed and destructive QI between the HOMO and strongly coupled
occupied orbitals of opposite phase is enhanced. We use a series of fluorene oligomers
containing a central benzothiadiazole10 unit to demonstrate that this strategy
can be used to create highly nonlinear single-molecule circuits. Notably, we are
able to reproducibly modulate the conductance of a 6-nm molecule by a factor of
more than 10^4.
article_processing_charge: No
author:
- first_name: Julia E.
full_name: Greenwald, Julia E.
last_name: Greenwald
- first_name: Joseph
full_name: Cameron, Joseph
last_name: Cameron
- first_name: Neil J.
full_name: Findlay, Neil J.
last_name: Findlay
- first_name: Tianren
full_name: Fu, Tianren
last_name: Fu
- first_name: Suman
full_name: Gunasekaran, Suman
last_name: Gunasekaran
- first_name: Peter J.
full_name: Skabara, Peter J.
last_name: Skabara
- first_name: Latha
full_name: Venkataraman, Latha
id: 9ebb78a5-cc0d-11ee-8322-fae086a32caf
last_name: Venkataraman
orcid: 0000-0002-6957-6089
citation:
ama: Greenwald JE, Cameron J, Findlay NJ, et al. Highly nonlinear transport across
single-molecule junctions via destructive quantum interference. Nature Nanotechnology.
2021;16(3):313-317. doi:10.1038/s41565-020-00807-x
apa: Greenwald, J. E., Cameron, J., Findlay, N. J., Fu, T., Gunasekaran, S., Skabara,
P. J., & Venkataraman, L. (2021). Highly nonlinear transport across single-molecule
junctions via destructive quantum interference. Nature Nanotechnology.
Springer Nature. https://doi.org/10.1038/s41565-020-00807-x
chicago: Greenwald, Julia E., Joseph Cameron, Neil J. Findlay, Tianren Fu, Suman
Gunasekaran, Peter J. Skabara, and Latha Venkataraman. “Highly Nonlinear Transport
across Single-Molecule Junctions via Destructive Quantum Interference.” Nature
Nanotechnology. Springer Nature, 2021. https://doi.org/10.1038/s41565-020-00807-x.
ieee: J. E. Greenwald et al., “Highly nonlinear transport across single-molecule
junctions via destructive quantum interference,” Nature Nanotechnology,
vol. 16, no. 3. Springer Nature, pp. 313–317, 2021.
ista: Greenwald JE, Cameron J, Findlay NJ, Fu T, Gunasekaran S, Skabara PJ, Venkataraman
L. 2021. Highly nonlinear transport across single-molecule junctions via destructive
quantum interference. Nature Nanotechnology. 16(3), 313–317.
mla: Greenwald, Julia E., et al. “Highly Nonlinear Transport across Single-Molecule
Junctions via Destructive Quantum Interference.” Nature Nanotechnology,
vol. 16, no. 3, Springer Nature, 2021, pp. 313–17, doi:10.1038/s41565-020-00807-x.
short: J.E. Greenwald, J. Cameron, N.J. Findlay, T. Fu, S. Gunasekaran, P.J. Skabara,
L. Venkataraman, Nature Nanotechnology 16 (2021) 313–317.
date_created: 2024-09-09T06:43:51Z
date_published: 2021-03-01T00:00:00Z
date_updated: 2024-12-10T10:20:32Z
day: '01'
doi: 10.1038/s41565-020-00807-x
extern: '1'
external_id:
pmid:
- '33288949'
intvolume: ' 16'
issue: '3'
language:
- iso: eng
month: '03'
oa_version: None
page: 313-317
pmid: 1
publication: Nature Nanotechnology
publication_identifier:
eissn:
- 1748-3395
issn:
- 1748-3387
publication_status: published
publisher: Springer Nature
quality_controlled: '1'
scopus_import: '1'
status: public
title: Highly nonlinear transport across single-molecule junctions via destructive
quantum interference
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 16
year: '2021'
...
---
OA_type: closed access
_id: '17901'
abstract:
- lang: eng
text: A 1,1,2,2-tetrakis(4-aminophenyl)ethene with three paths of π-conjugation,
linear-cis, linear-trans and a cross-conjugation, has been prepared. The molecule
is able to bind to gold electrodes forming molecular junctions for single-molecule
conductance measurements. Only two regimes of conduction are found experimentally.
The modelling of the conductance allows to assign them to through-bond transmission
in the linear case, while the cross-conjugated channel is further assisted by
through-space transmission, partially alleviating the destructive quantum interference.
article_processing_charge: No
article_type: original
author:
- first_name: Samara
full_name: Medina Rivero, Samara
last_name: Medina Rivero
- first_name: Paloma
full_name: García Arroyo, Paloma
last_name: García Arroyo
- first_name: Liang
full_name: Li, Liang
last_name: Li
- first_name: Suman
full_name: Gunasekaran, Suman
last_name: Gunasekaran
- first_name: Thijs
full_name: Stuyver, Thijs
last_name: Stuyver
- first_name: María José
full_name: Mancheño, María José
last_name: Mancheño
- first_name: Mercedes
full_name: Alonso, Mercedes
last_name: Alonso
- first_name: Latha
full_name: Venkataraman, Latha
id: 9ebb78a5-cc0d-11ee-8322-fae086a32caf
last_name: Venkataraman
orcid: 0000-0002-6957-6089
- first_name: José L.
full_name: Segura, José L.
last_name: Segura
- first_name: Juan
full_name: Casado, Juan
last_name: Casado
citation:
ama: Medina Rivero S, García Arroyo P, Li L, et al. Single-molecule conductance
in a unique cross-conjugated tetra(aminoaryl)ethene. Chemical Communications.
2021;57(5):591-594. doi:10.1039/d0cc07124b
apa: Medina Rivero, S., García Arroyo, P., Li, L., Gunasekaran, S., Stuyver, T.,
Mancheño, M. J., … Casado, J. (2021). Single-molecule conductance in a unique
cross-conjugated tetra(aminoaryl)ethene. Chemical Communications. Royal
Society of Chemistry. https://doi.org/10.1039/d0cc07124b
chicago: Medina Rivero, Samara, Paloma García Arroyo, Liang Li, Suman Gunasekaran,
Thijs Stuyver, María José Mancheño, Mercedes Alonso, Latha Venkataraman, José
L. Segura, and Juan Casado. “Single-Molecule Conductance in a Unique Cross-Conjugated
Tetra(Aminoaryl)Ethene.” Chemical Communications. Royal Society of Chemistry,
2021. https://doi.org/10.1039/d0cc07124b.
ieee: S. Medina Rivero et al., “Single-molecule conductance in a unique cross-conjugated
tetra(aminoaryl)ethene,” Chemical Communications, vol. 57, no. 5. Royal
Society of Chemistry, pp. 591–594, 2021.
ista: Medina Rivero S, García Arroyo P, Li L, Gunasekaran S, Stuyver T, Mancheño
MJ, Alonso M, Venkataraman L, Segura JL, Casado J. 2021. Single-molecule conductance
in a unique cross-conjugated tetra(aminoaryl)ethene. Chemical Communications.
57(5), 591–594.
mla: Medina Rivero, Samara, et al. “Single-Molecule Conductance in a Unique Cross-Conjugated
Tetra(Aminoaryl)Ethene.” Chemical Communications, vol. 57, no. 5, Royal
Society of Chemistry, 2021, pp. 591–94, doi:10.1039/d0cc07124b.
short: S. Medina Rivero, P. García Arroyo, L. Li, S. Gunasekaran, T. Stuyver, M.J.
Mancheño, M. Alonso, L. Venkataraman, J.L. Segura, J. Casado, Chemical Communications
57 (2021) 591–594.
date_created: 2024-09-09T06:44:58Z
date_published: 2021-05-01T00:00:00Z
date_updated: 2024-12-10T10:23:49Z
day: '01'
doi: 10.1039/d0cc07124b
extern: '1'
external_id:
pmid:
- '33325935'
intvolume: ' 57'
issue: '5'
language:
- iso: eng
month: '05'
oa_version: None
page: 591-594
pmid: 1
publication: Chemical Communications
publication_identifier:
eissn:
- 1364-548X
issn:
- 1359-7345
publication_status: published
publisher: Royal Society of Chemistry
quality_controlled: '1'
scopus_import: '1'
status: public
title: Single-molecule conductance in a unique cross-conjugated tetra(aminoaryl)ethene
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 57
year: '2021'
...
---
_id: '18192'
abstract:
- lang: eng
text: Current quantum simulation experiments are starting to explore nonequilibrium
many-body dynamics in previously inaccessible regimes in terms of system sizes
and timescales. Therefore, the question emerges as to which observables are best
suited to study the dynamics in such quantum many-body systems. Using machine
learning techniques, we investigate the dynamics and, in particular, the thermalization
behavior of an interacting quantum system that undergoes a nonequilibrium phase
transition from an ergodic to a many-body localized phase. We employ supervised
and unsupervised training methods to distinguish nonequilibrium from equilibrium
data, using the network performance as a probe for the thermalization behavior
of the system. We test our methods with experimental snapshots of ultracold atoms
taken with a quantum gas microscope. Our results provide a path to analyze highly
entangled large-scale quantum states for system sizes where numerical calculations
of conventional observables become challenging.
article_number: '150504'
article_processing_charge: No
article_type: original
arxiv: 1
author:
- first_name: A.
full_name: Bohrdt, A.
last_name: Bohrdt
- first_name: S.
full_name: Kim, S.
last_name: Kim
- first_name: A.
full_name: Lukin, A.
last_name: Lukin
- first_name: M.
full_name: Rispoli, M.
last_name: Rispoli
- first_name: R.
full_name: Schittko, R.
last_name: Schittko
- first_name: M.
full_name: Knap, M.
last_name: Knap
- first_name: M.
full_name: Greiner, M.
last_name: Greiner
- first_name: Julian
full_name: Leonard, Julian
id: b75b3f45-7995-11ef-9bfd-9a9cd02c3577
last_name: Leonard
citation:
ama: Bohrdt A, Kim S, Lukin A, et al. Analyzing nonequilibrium quantum states through
snapshots with artificial neural networks. Physical Review Letters. 2021;127(15).
doi:10.1103/physrevlett.127.150504
apa: Bohrdt, A., Kim, S., Lukin, A., Rispoli, M., Schittko, R., Knap, M., … Leonard,
J. (2021). Analyzing nonequilibrium quantum states through snapshots with artificial
neural networks. Physical Review Letters. American Physical Society. https://doi.org/10.1103/physrevlett.127.150504
chicago: Bohrdt, A., S. Kim, A. Lukin, M. Rispoli, R. Schittko, M. Knap, M. Greiner,
and Julian Leonard. “Analyzing Nonequilibrium Quantum States through Snapshots
with Artificial Neural Networks.” Physical Review Letters. American Physical
Society, 2021. https://doi.org/10.1103/physrevlett.127.150504.
ieee: A. Bohrdt et al., “Analyzing nonequilibrium quantum states through
snapshots with artificial neural networks,” Physical Review Letters, vol.
127, no. 15. American Physical Society, 2021.
ista: Bohrdt A, Kim S, Lukin A, Rispoli M, Schittko R, Knap M, Greiner M, Leonard
J. 2021. Analyzing nonequilibrium quantum states through snapshots with artificial
neural networks. Physical Review Letters. 127(15), 150504.
mla: Bohrdt, A., et al. “Analyzing Nonequilibrium Quantum States through Snapshots
with Artificial Neural Networks.” Physical Review Letters, vol. 127, no.
15, 150504, American Physical Society, 2021, doi:10.1103/physrevlett.127.150504.
short: A. Bohrdt, S. Kim, A. Lukin, M. Rispoli, R. Schittko, M. Knap, M. Greiner,
J. Leonard, Physical Review Letters 127 (2021).
date_created: 2024-10-07T11:47:11Z
date_published: 2021-10-08T00:00:00Z
date_updated: 2024-10-08T09:58:03Z
day: '08'
doi: 10.1103/physrevlett.127.150504
extern: '1'
external_id:
arxiv:
- '2012.11586'
intvolume: ' 127'
issue: '15'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.2012.11586
month: '10'
oa: 1
oa_version: Preprint
publication: Physical Review Letters
publication_identifier:
issn:
- 0031-9007
- 1079-7114
publication_status: published
publisher: American Physical Society
quality_controlled: '1'
scopus_import: '1'
status: public
title: Analyzing nonequilibrium quantum states through snapshots with artificial neural
networks
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 127
year: '2021'
...
---
_id: '18193'
abstract:
- lang: eng
text: "Topological states of matter, such as fractional quantum Hall states, are
an active field of research due to their exotic excitations. In particular, ultracold
atoms in optical lattices provide a highly controllable and adaptable platform
to study such new types of quantum matter. However, finding a clear route to realize
non-Abelian quantum Hall states in these systems remains challenging. Here we
use the density-matrix renormalization-group (DMRG) method to study the Hofstadter-Bose-Hubbard
model at filling factor \U0001D708=1 and find strong indications that at \U0001D6FC=1/6
magnetic flux quanta per plaquette the ground state is a lattice analog of the
continuum non-Abelian Pfaffian. We study the on-site correlations of the ground
state, which indicate its paired nature at \U0001D708=1, and find an incompressible
state characterized by a charge gap in the bulk. We argue that the emergence of
a charge density wave on thin cylinders and the behavior of the two- and three-particle
correlation functions at short distances provide evidence for the state being
closely related to the continuum Pfaffian. The signatures discussed in this letter
are accessible in current cold atom experiments and we show that the Pfaffian-like
state is readily realizable in few-body systems using adiabatic preparation schemes."
article_number: L161101
article_processing_charge: No
article_type: letter_note
arxiv: 1
author:
- first_name: F. A.
full_name: Palm, F. A.
last_name: Palm
- first_name: M.
full_name: Buser, M.
last_name: Buser
- first_name: Julian
full_name: Leonard, Julian
id: b75b3f45-7995-11ef-9bfd-9a9cd02c3577
last_name: Leonard
- first_name: M.
full_name: Aidelsburger, M.
last_name: Aidelsburger
- first_name: U.
full_name: Schollwöck, U.
last_name: Schollwöck
- first_name: F.
full_name: Grusdt, F.
last_name: Grusdt
citation:
ama: Palm FA, Buser M, Leonard J, Aidelsburger M, Schollwöck U, Grusdt F. Bosonic
Pfaffian state in the Hofstadter-Bose-Hubbard model. Physical Review B.
2021;103(16). doi:10.1103/physrevb.103.l161101
apa: Palm, F. A., Buser, M., Leonard, J., Aidelsburger, M., Schollwöck, U., &
Grusdt, F. (2021). Bosonic Pfaffian state in the Hofstadter-Bose-Hubbard model.
Physical Review B. American Physical Society. https://doi.org/10.1103/physrevb.103.l161101
chicago: Palm, F. A., M. Buser, Julian Leonard, M. Aidelsburger, U. Schollwöck,
and F. Grusdt. “Bosonic Pfaffian State in the Hofstadter-Bose-Hubbard Model.”
Physical Review B. American Physical Society, 2021. https://doi.org/10.1103/physrevb.103.l161101.
ieee: F. A. Palm, M. Buser, J. Leonard, M. Aidelsburger, U. Schollwöck, and F. Grusdt,
“Bosonic Pfaffian state in the Hofstadter-Bose-Hubbard model,” Physical Review
B, vol. 103, no. 16. American Physical Society, 2021.
ista: Palm FA, Buser M, Leonard J, Aidelsburger M, Schollwöck U, Grusdt F. 2021.
Bosonic Pfaffian state in the Hofstadter-Bose-Hubbard model. Physical Review B.
103(16), L161101.
mla: Palm, F. A., et al. “Bosonic Pfaffian State in the Hofstadter-Bose-Hubbard
Model.” Physical Review B, vol. 103, no. 16, L161101, American Physical
Society, 2021, doi:10.1103/physrevb.103.l161101.
short: F.A. Palm, M. Buser, J. Leonard, M. Aidelsburger, U. Schollwöck, F. Grusdt,
Physical Review B 103 (2021).
date_created: 2024-10-07T11:47:51Z
date_published: 2021-04-15T00:00:00Z
date_updated: 2024-10-08T09:55:46Z
day: '15'
doi: 10.1103/physrevb.103.l161101
extern: '1'
external_id:
arxiv:
- '2011.02477'
intvolume: ' 103'
issue: '16'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.2011.02477
month: '04'
oa: 1
oa_version: Preprint
publication: Physical Review B
publication_identifier:
eissn:
- 2469-9969
issn:
- 2469-9950
publication_status: published
publisher: American Physical Society
quality_controlled: '1'
scopus_import: '1'
status: public
title: Bosonic Pfaffian state in the Hofstadter-Bose-Hubbard model
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 103
year: '2021'
...
---
OA_place: repository
OA_type: green
_id: '18233'
abstract:
- lang: eng
text: Neural network quantization enables the deployment of large models on resource-constrained
devices. Current post-training quantization methods fall short in terms of accuracy
for INT4 (or lower) but provide reasonable accuracy for INT8 (or above). In this
work, we study the effect of quantization on the structure of the loss landscape.
We show that the structure is flat and separable for mild quantization, enabling
straightforward post-training quantization methods to achieve good results. We
show that with more aggressive quantization, the loss landscape becomes highly
non-separable with steep curvature, making the selection of quantization parameters
more challenging. Armed with this understanding, we design a method that quantizes
the layer parameters jointly, enabling significant accuracy improvement over current
post-training quantization methods. Reference implementation is available at https://github.com/ynahshan/nn-quantization-pytorch/tree/master/lapq.
article_processing_charge: No
article_type: original
arxiv: 1
author:
- first_name: Yury
full_name: Nahshan, Yury
last_name: Nahshan
- first_name: Brian
full_name: Chmiel, Brian
last_name: Chmiel
- first_name: Chaim
full_name: Baskin, Chaim
last_name: Baskin
- first_name: Evgenii
full_name: Zheltonozhskii, Evgenii
last_name: Zheltonozhskii
- first_name: Ron
full_name: Banner, Ron
last_name: Banner
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Avi
full_name: Mendelson, Avi
last_name: Mendelson
citation:
ama: Nahshan Y, Chmiel B, Baskin C, et al. Loss aware post-training quantization.
Machine Learning. 2021;110(11-12):3245-3262. doi:10.1007/s10994-021-06053-z
apa: Nahshan, Y., Chmiel, B., Baskin, C., Zheltonozhskii, E., Banner, R., Bronstein,
A. M., & Mendelson, A. (2021). Loss aware post-training quantization. Machine
Learning. Springer Nature. https://doi.org/10.1007/s10994-021-06053-z
chicago: Nahshan, Yury, Brian Chmiel, Chaim Baskin, Evgenii Zheltonozhskii, Ron
Banner, Alex M. Bronstein, and Avi Mendelson. “Loss Aware Post-Training Quantization.”
Machine Learning. Springer Nature, 2021. https://doi.org/10.1007/s10994-021-06053-z.
ieee: Y. Nahshan et al., “Loss aware post-training quantization,” Machine
Learning, vol. 110, no. 11–12. Springer Nature, pp. 3245–3262, 2021.
ista: Nahshan Y, Chmiel B, Baskin C, Zheltonozhskii E, Banner R, Bronstein AM, Mendelson
A. 2021. Loss aware post-training quantization. Machine Learning. 110(11–12),
3245–3262.
mla: Nahshan, Yury, et al. “Loss Aware Post-Training Quantization.” Machine Learning,
vol. 110, no. 11–12, Springer Nature, 2021, pp. 3245–62, doi:10.1007/s10994-021-06053-z.
short: Y. Nahshan, B. Chmiel, C. Baskin, E. Zheltonozhskii, R. Banner, A.M. Bronstein,
A. Mendelson, Machine Learning 110 (2021) 3245–3262.
date_created: 2024-10-08T12:57:05Z
date_published: 2021-12-01T00:00:00Z
date_updated: 2024-10-15T07:33:28Z
day: '01'
doi: 10.1007/s10994-021-06053-z
extern: '1'
external_id:
arxiv:
- '1911.07190'
intvolume: ' 110'
issue: 11-12
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.1911.07190
month: '12'
oa: 1
oa_version: Preprint
page: 3245-3262
publication: Machine Learning
publication_identifier:
eissn:
- 1573-0565
issn:
- 0885-6125
publication_status: published
publisher: Springer Nature
quality_controlled: '1'
related_material:
link:
- relation: software
url: https://github.com/ynahshan/nn-quantization-pytorch/tree/master/lapq
scopus_import: '1'
status: public
title: Loss aware post-training quantization
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 110
year: '2021'
...
---
DOAJ_listed: '1'
OA_place: publisher
OA_type: gold
_id: '18234'
abstract:
- lang: eng
text: Convolutional Neural Networks (CNNs) are very popular in many fields including
computer vision, speech recognition, natural language processing, etc. Though
deep learning leads to groundbreaking performance in those domains, the networks
used are very computationally demanding and are far from being able to perform
in real-time applications even on a GPU, which is not power efficient and therefore
does not suit low power systems such as mobile devices. To overcome this challenge,
some solutions have been proposed for quantizing the weights and activations of
these networks, which accelerate the runtime significantly. Yet, this acceleration
comes at the cost of a larger error unless spatial adjustments are carried out.
The method proposed in this work trains quantized neural networks by noise injection
and a learned clamping, which improve accuracy. This leads to state-of-the-art
results on various regression and classification tasks, e.g., ImageNet classification
with architectures such as ResNet-18/34/50 with as low as 3 bit weights and activations.
We implement the proposed solution on an FPGA to demonstrate its applicability
for low-power real-time applications. The quantization code will become publicly
available upon acceptance.
article_number: '2144'
article_processing_charge: No
article_type: original
arxiv: 1
author:
- first_name: Chaim
full_name: Baskin, Chaim
last_name: Baskin
- first_name: Evgenii
full_name: Zheltonozhkii, Evgenii
last_name: Zheltonozhkii
- first_name: Tal
full_name: Rozen, Tal
last_name: Rozen
- first_name: Natan
full_name: Liss, Natan
last_name: Liss
- first_name: Yoav
full_name: Chai, Yoav
last_name: Chai
- first_name: Eli
full_name: Schwartz, Eli
last_name: Schwartz
- first_name: Raja
full_name: Giryes, Raja
last_name: Giryes
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Avi
full_name: Mendelson, Avi
last_name: Mendelson
citation:
ama: 'Baskin C, Zheltonozhkii E, Rozen T, et al. NICE: Noise Injection and Clamping
Estimation for neural network quantization. Mathematics. 2021;9(17). doi:10.3390/math9172144'
apa: 'Baskin, C., Zheltonozhkii, E., Rozen, T., Liss, N., Chai, Y., Schwartz, E.,
… Mendelson, A. (2021). NICE: Noise Injection and Clamping Estimation for neural
network quantization. Mathematics. MDPI. https://doi.org/10.3390/math9172144'
chicago: 'Baskin, Chaim, Evgenii Zheltonozhkii, Tal Rozen, Natan Liss, Yoav Chai,
Eli Schwartz, Raja Giryes, Alex M. Bronstein, and Avi Mendelson. “NICE: Noise
Injection and Clamping Estimation for Neural Network Quantization.” Mathematics.
MDPI, 2021. https://doi.org/10.3390/math9172144.'
ieee: 'C. Baskin et al., “NICE: Noise Injection and Clamping Estimation for
neural network quantization,” Mathematics, vol. 9, no. 17. MDPI, 2021.'
ista: 'Baskin C, Zheltonozhkii E, Rozen T, Liss N, Chai Y, Schwartz E, Giryes R,
Bronstein AM, Mendelson A. 2021. NICE: Noise Injection and Clamping Estimation
for neural network quantization. Mathematics. 9(17), 2144.'
mla: 'Baskin, Chaim, et al. “NICE: Noise Injection and Clamping Estimation for Neural
Network Quantization.” Mathematics, vol. 9, no. 17, 2144, MDPI, 2021, doi:10.3390/math9172144.'
short: C. Baskin, E. Zheltonozhkii, T. Rozen, N. Liss, Y. Chai, E. Schwartz, R.
Giryes, A.M. Bronstein, A. Mendelson, Mathematics 9 (2021).
date_created: 2024-10-08T12:57:24Z
date_published: 2021-09-02T00:00:00Z
date_updated: 2024-10-15T07:37:39Z
day: '02'
doi: 10.3390/math9172144
extern: '1'
external_id:
arxiv:
- '1810.00162'
intvolume: ' 9'
issue: '17'
language:
- iso: eng
month: '09'
oa_version: Published Version
publication: Mathematics
publication_identifier:
issn:
- 2227-7390
publication_status: published
publisher: MDPI
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'NICE: Noise Injection and Clamping Estimation for neural network quantization'
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 9
year: '2021'
...
---
OA_place: repository
OA_type: green
_id: '18235'
abstract:
- lang: eng
text: 'Recently, great progress has been made in the field of Few-Shot Learning
(FSL). While many different methods have been proposed, one of the key factors
leading to higher FSL performance is surprisingly simple. It is the backbone network
architecture used to embed the images of the few-shot tasks. While first works
on FSL resorted to small architectures with just a few convolution layers, recent
works show that large architectures pre-trained on the training portion of FSL
datasets produce strong features that are more easily transferable to novel few-shot
tasks, thus attaining significant gains to methods using them. Despite these observations,
little to no work has been done towards finding the right backbone for FSL. In
this paper we propose MetAdapt that not only meta-searches for an optimized architecture
for FSL using Network Architecture Search (NAS), but also results in a model that
can adaptively ‘re-wire’ itself predicting the better architecture for a given
novel few-shot task. Using the proposed approach we observe strong results on
two popular few-shot benchmarks: miniImageNet and FC100.'
article_processing_charge: No
article_type: original
arxiv: 1
author:
- first_name: Sivan
full_name: Doveh, Sivan
last_name: Doveh
- first_name: Eli
full_name: Schwartz, Eli
last_name: Schwartz
- first_name: Chao
full_name: Xue, Chao
last_name: Xue
- first_name: Rogerio
full_name: Feris, Rogerio
last_name: Feris
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Raja
full_name: Giryes, Raja
last_name: Giryes
- first_name: Leonid
full_name: Karlinsky, Leonid
last_name: Karlinsky
citation:
ama: 'Doveh S, Schwartz E, Xue C, et al. MetAdapt: Meta-learned task-adaptive architecture
for few-shot classification. Pattern Recognition Letters. 2021;149:130-136.
doi:10.1016/j.patrec.2021.05.010'
apa: 'Doveh, S., Schwartz, E., Xue, C., Feris, R., Bronstein, A. M., Giryes, R.,
& Karlinsky, L. (2021). MetAdapt: Meta-learned task-adaptive architecture
for few-shot classification. Pattern Recognition Letters. Elsevier. https://doi.org/10.1016/j.patrec.2021.05.010'
chicago: 'Doveh, Sivan, Eli Schwartz, Chao Xue, Rogerio Feris, Alex M. Bronstein,
Raja Giryes, and Leonid Karlinsky. “MetAdapt: Meta-Learned Task-Adaptive Architecture
for Few-Shot Classification.” Pattern Recognition Letters. Elsevier, 2021.
https://doi.org/10.1016/j.patrec.2021.05.010.'
ieee: 'S. Doveh et al., “MetAdapt: Meta-learned task-adaptive architecture
for few-shot classification,” Pattern Recognition Letters, vol. 149. Elsevier,
pp. 130–136, 2021.'
ista: 'Doveh S, Schwartz E, Xue C, Feris R, Bronstein AM, Giryes R, Karlinsky L.
2021. MetAdapt: Meta-learned task-adaptive architecture for few-shot classification.
Pattern Recognition Letters. 149, 130–136.'
mla: 'Doveh, Sivan, et al. “MetAdapt: Meta-Learned Task-Adaptive Architecture for
Few-Shot Classification.” Pattern Recognition Letters, vol. 149, Elsevier,
2021, pp. 130–36, doi:10.1016/j.patrec.2021.05.010.'
short: S. Doveh, E. Schwartz, C. Xue, R. Feris, A.M. Bronstein, R. Giryes, L. Karlinsky,
Pattern Recognition Letters 149 (2021) 130–136.
date_created: 2024-10-08T12:57:53Z
date_published: 2021-09-01T00:00:00Z
date_updated: 2024-10-15T07:39:56Z
day: '01'
doi: 10.1016/j.patrec.2021.05.010
extern: '1'
external_id:
arxiv:
- '1912.00412'
intvolume: ' 149'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.1912.00412
month: '09'
oa: 1
oa_version: Preprint
page: 130-136
publication: Pattern Recognition Letters
publication_identifier:
issn:
- 0167-8655
publication_status: published
publisher: Elsevier
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'MetAdapt: Meta-learned task-adaptive architecture for few-shot classification'
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 149
year: '2021'
...
---
OA_place: publisher
OA_type: free access
_id: '18236'
abstract:
- lang: eng
text: 'Despite their great promise, artificial intelligence (AI) systems have yet
to become ubiquitous in the daily practice of medicine largely due to several
crucial unmet needs of healthcare practitioners. These include lack of explanations
in clinically meaningful terms, handling the presence of unknown medical conditions,
and transparency regarding the system’s limitations, both in terms of statistical
performance as well as recognizing situations for which the system’s predictions
are irrelevant. We articulate these unmet clinical needs as machine-learning (ML)
problems and systematically address them with cutting-edge ML techniques. We focus
on electrocardiogram (ECG) analysis as an example domain in which AI has great
potential and tackle two challenging tasks: the detection of a heterogeneous mix
of known and unknown arrhythmias from ECG and the identification of underlying
cardio-pathology from segments annotated as normal sinus rhythm recorded in patients
with an intermittent arrhythmia. We validate our methods by simulating a screening
for arrhythmias in a large-scale population while adhering to statistical significance
requirements. Specifically, our system 1) visualizes the relative importance of
each part of an ECG segment for the final model decision; 2) upholds specified
statistical constraints on its out-of-sample performance and provides uncertainty
estimation for its predictions; 3) handles inputs containing unknown rhythm types;
and 4) handles data from unseen patients while also flagging cases in which the
model’s outputs are not usable for a specific patient. This work represents a
significant step toward overcoming the limitations currently impeding the integration
of AI into clinical practice in cardiology and medicine in general.'
article_number: e2020620118
article_processing_charge: No
article_type: original
author:
- first_name: Yonatan
full_name: Elul, Yonatan
last_name: Elul
- first_name: Aviv A.
full_name: Rosenberg, Aviv A.
last_name: Rosenberg
- first_name: Assaf
full_name: Schuster, Assaf
last_name: Schuster
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Yael
full_name: Yaniv, Yael
last_name: Yaniv
citation:
ama: Elul Y, Rosenberg AA, Schuster A, Bronstein AM, Yaniv Y. Meeting the unmet
needs of clinicians from AI systems showcased for cardiology with deep-learning–based
ECG analysis. Proceedings of the National Academy of Sciences. 2021;118(24).
doi:10.1073/pnas.2020620118
apa: Elul, Y., Rosenberg, A. A., Schuster, A., Bronstein, A. M., & Yaniv, Y.
(2021). Meeting the unmet needs of clinicians from AI systems showcased for cardiology
with deep-learning–based ECG analysis. Proceedings of the National Academy
of Sciences. National Academy of Sciences. https://doi.org/10.1073/pnas.2020620118
chicago: Elul, Yonatan, Aviv A. Rosenberg, Assaf Schuster, Alex M. Bronstein, and
Yael Yaniv. “Meeting the Unmet Needs of Clinicians from AI Systems Showcased for
Cardiology with Deep-Learning–Based ECG Analysis.” Proceedings of the National
Academy of Sciences. National Academy of Sciences, 2021. https://doi.org/10.1073/pnas.2020620118.
ieee: Y. Elul, A. A. Rosenberg, A. Schuster, A. M. Bronstein, and Y. Yaniv, “Meeting
the unmet needs of clinicians from AI systems showcased for cardiology with deep-learning–based
ECG analysis,” Proceedings of the National Academy of Sciences, vol. 118,
no. 24. National Academy of Sciences, 2021.
ista: Elul Y, Rosenberg AA, Schuster A, Bronstein AM, Yaniv Y. 2021. Meeting the
unmet needs of clinicians from AI systems showcased for cardiology with deep-learning–based
ECG analysis. Proceedings of the National Academy of Sciences. 118(24), e2020620118.
mla: Elul, Yonatan, et al. “Meeting the Unmet Needs of Clinicians from AI Systems
Showcased for Cardiology with Deep-Learning–Based ECG Analysis.” Proceedings
of the National Academy of Sciences, vol. 118, no. 24, e2020620118, National
Academy of Sciences, 2021, doi:10.1073/pnas.2020620118.
short: Y. Elul, A.A. Rosenberg, A. Schuster, A.M. Bronstein, Y. Yaniv, Proceedings
of the National Academy of Sciences 118 (2021).
date_created: 2024-10-08T12:58:09Z
date_published: 2021-06-07T00:00:00Z
date_updated: 2024-10-15T07:43:01Z
day: '07'
doi: 10.1073/pnas.2020620118
extern: '1'
external_id:
pmid:
- '34099565'
intvolume: ' 118'
issue: '24'
language:
- iso: eng
month: '06'
oa_version: Published Version
pmid: 1
publication: Proceedings of the National Academy of Sciences
publication_identifier:
eissn:
- 1091-6490
issn:
- 0027-8424
publication_status: published
publisher: National Academy of Sciences
quality_controlled: '1'
scopus_import: '1'
status: public
title: Meeting the unmet needs of clinicians from AI systems showcased for cardiology
with deep-learning–based ECG analysis
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 118
year: '2021'
...
---
OA_place: repository
OA_type: green
_id: '18237'
abstract:
- lang: eng
text: We present a novel method for neural network quantization. Our method, named
UNIQ, emulates a non-uniform k-quantile quantizer and adapts the model to perform
well with quantized weights by injecting noise to the weights at training time.
As a by-product of injecting noise to weights, we find that activations can also
be quantized to as low as 8-bit with only a minor accuracy degradation. Our non-uniform
quantization approach provides a novel alternative to the existing uniform quantization
techniques for neural networks. We further propose a novel complexity metric of
number of bit operations performed (BOPs), and we show that this metric has a
linear relation with logic utilization and power. We suggest evaluating the trade-off
of accuracy vs. complexity (BOPs). The proposed method, when evaluated on ResNet18/34/50
and MobileNet on ImageNet, outperforms the prior state of the art both in the
low-complexity regime and the high accuracy regime. We demonstrate the practical
applicability of this approach, by implementing our non-uniformly quantized CNN
on FPGA.
article_processing_charge: No
article_type: original
arxiv: 1
author:
- first_name: Chaim
full_name: Baskin, Chaim
last_name: Baskin
- first_name: Natan
full_name: Liss, Natan
last_name: Liss
- first_name: Eli
full_name: Schwartz, Eli
last_name: Schwartz
- first_name: Evgenii
full_name: Zheltonozhskii, Evgenii
last_name: Zheltonozhskii
- first_name: Raja
full_name: Giryes, Raja
last_name: Giryes
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Avi
full_name: Mendelson, Avi
last_name: Mendelson
citation:
ama: 'Baskin C, Liss N, Schwartz E, et al. UNIQ: Uniform Noise Injection for Non-Uniform
Quantization of neural networks. ACM Transactions on Computer Systems.
2021;37(1-4):1-15. doi:10.1145/3444943'
apa: 'Baskin, C., Liss, N., Schwartz, E., Zheltonozhskii, E., Giryes, R., Bronstein,
A. M., & Mendelson, A. (2021). UNIQ: Uniform Noise Injection for Non-Uniform
Quantization of neural networks. ACM Transactions on Computer Systems.
Association for Computing Machinery. https://doi.org/10.1145/3444943'
chicago: 'Baskin, Chaim, Natan Liss, Eli Schwartz, Evgenii Zheltonozhskii, Raja
Giryes, Alex M. Bronstein, and Avi Mendelson. “UNIQ: Uniform Noise Injection for
Non-Uniform Quantization of Neural Networks.” ACM Transactions on Computer
Systems. Association for Computing Machinery, 2021. https://doi.org/10.1145/3444943.'
ieee: 'C. Baskin et al., “UNIQ: Uniform Noise Injection for Non-Uniform Quantization
of neural networks,” ACM Transactions on Computer Systems, vol. 37, no.
1–4. Association for Computing Machinery, pp. 1–15, 2021.'
ista: 'Baskin C, Liss N, Schwartz E, Zheltonozhskii E, Giryes R, Bronstein AM, Mendelson
A. 2021. UNIQ: Uniform Noise Injection for Non-Uniform Quantization of neural
networks. ACM Transactions on Computer Systems. 37(1–4), 1–15.'
mla: 'Baskin, Chaim, et al. “UNIQ: Uniform Noise Injection for Non-Uniform Quantization
of Neural Networks.” ACM Transactions on Computer Systems, vol. 37, no.
1–4, Association for Computing Machinery, 2021, pp. 1–15, doi:10.1145/3444943.'
short: C. Baskin, N. Liss, E. Schwartz, E. Zheltonozhskii, R. Giryes, A.M. Bronstein,
A. Mendelson, ACM Transactions on Computer Systems 37 (2021) 1–15.
date_created: 2024-10-08T12:58:26Z
date_published: 2021-03-26T00:00:00Z
date_updated: 2024-10-15T07:47:22Z
day: '26'
doi: 10.1145/3444943
extern: '1'
external_id:
arxiv:
- '1804.10969'
intvolume: ' 37'
issue: 1-4
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.1804.10969
month: '03'
oa: 1
oa_version: Preprint
page: 1-15
publication: ACM Transactions on Computer Systems
publication_identifier:
eissn:
- 1557-7333
issn:
- 0734-2071
publication_status: published
publisher: Association for Computing Machinery
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'UNIQ: Uniform Noise Injection for Non-Uniform Quantization of neural networks'
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 37
year: '2021'
...
---
OA_place: publisher
OA_type: gold
_id: '18238'
abstract:
- lang: eng
text: The demand for running NNs in embedded environments has increased significantly
in recent years due to the significant success of convolutional neural network
(CNN) approaches in various tasks, including image recognition and generation.
The task of achieving high accuracy on resource-restricted devices, however, is
still considered to be challenging, which is mainly due to the vast number of
design parameters that need to be balanced. While the quantization of CNN parameters
leads to a reduction of power and area, it can also generate unexpected changes
in the balance between communication and computation. This change is hard to evaluate,
and the lack of balance may lead to lower utilization of either memory bandwidth
or computational resources, thereby reducing performance. This paper introduces
a hardware performance analysis framework for identifying bottlenecks in the early
stages of CNN hardware design. We demonstrate how the proposed method can help
in evaluating different architecture alternatives of resource-restricted CNN accelerators
(e.g., part of real-time embedded systems) early in design stages and, thus, prevent
making design mistakes.
article_number: '717'
article_processing_charge: No
article_type: original
author:
- first_name: Alex
full_name: Karbachevsky, Alex
last_name: Karbachevsky
- first_name: Chaim
full_name: Baskin, Chaim
last_name: Baskin
- first_name: Evgenii
full_name: Zheltonozhskii, Evgenii
last_name: Zheltonozhskii
- first_name: Yevgeny
full_name: Yermolin, Yevgeny
last_name: Yermolin
- first_name: Freddy
full_name: Gabbay, Freddy
last_name: Gabbay
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Avi
full_name: Mendelson, Avi
last_name: Mendelson
citation:
ama: Karbachevsky A, Baskin C, Zheltonozhskii E, et al. Early-stage neural network
hardware performance analysis. Sustainability. 2021;13(2). doi:10.3390/su13020717
apa: Karbachevsky, A., Baskin, C., Zheltonozhskii, E., Yermolin, Y., Gabbay, F.,
Bronstein, A. M., & Mendelson, A. (2021). Early-stage neural network hardware
performance analysis. Sustainability. MDPI. https://doi.org/10.3390/su13020717
chicago: Karbachevsky, Alex, Chaim Baskin, Evgenii Zheltonozhskii, Yevgeny Yermolin,
Freddy Gabbay, Alex M. Bronstein, and Avi Mendelson. “Early-Stage Neural Network
Hardware Performance Analysis.” Sustainability. MDPI, 2021. https://doi.org/10.3390/su13020717.
ieee: A. Karbachevsky et al., “Early-stage neural network hardware performance
analysis,” Sustainability, vol. 13, no. 2. MDPI, 2021.
ista: Karbachevsky A, Baskin C, Zheltonozhskii E, Yermolin Y, Gabbay F, Bronstein
AM, Mendelson A. 2021. Early-stage neural network hardware performance analysis.
Sustainability. 13(2), 717.
mla: Karbachevsky, Alex, et al. “Early-Stage Neural Network Hardware Performance
Analysis.” Sustainability, vol. 13, no. 2, 717, MDPI, 2021, doi:10.3390/su13020717.
short: A. Karbachevsky, C. Baskin, E. Zheltonozhskii, Y. Yermolin, F. Gabbay, A.M.
Bronstein, A. Mendelson, Sustainability 13 (2021).
date_created: 2024-10-08T12:58:47Z
date_published: 2021-01-13T00:00:00Z
date_updated: 2024-10-15T08:17:49Z
day: '13'
doi: 10.3390/su13020717
extern: '1'
intvolume: ' 13'
issue: '2'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.3390/su13020717
month: '01'
oa: 1
oa_version: Published Version
publication: Sustainability
publication_identifier:
issn:
- 2071-1050
publication_status: published
publisher: MDPI
quality_controlled: '1'
scopus_import: '1'
status: public
title: Early-stage neural network hardware performance analysis
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 13
year: '2021'
...
---
OA_place: repository
OA_type: green
_id: '18239'
abstract:
- lang: eng
text: Nowadays, there is an abundance of data involving images and surrounding free-form
text weakly corresponding to those images. Weakly Supervised phrase-Grounding
(WSG) deals with the task of using this data to learn to localize (or to ground)
arbitrary text phrases in images without any additional annotations. However,
most recent SotA methods for WSG assume an existence of a pre-trained object detector,
relying on it to produce the ROIs for localization. In this work, we focus on
the task of Detector-Free WSG (DF-WSG) to solve WSG without relying on a pre-trained
detector. The key idea behind our proposed Grounding by Separation (GbS) method
is synthesizing ‘text to image-regions’ associations by random alpha-blending
of arbitrary image pairs and using the corresponding texts of the pair as conditions
to recover the alpha map from the blended image via a segmentation network. At
test time, this allows using the query phrase as a condition for a non-blended
query image, thus interpreting the test image as a composition of a region corresponding
to the phrase and the complement region. Our GbS shows an 8.5% accuracy improvement
over previous DF-WSG SotA, for a range of benchmarks including Flickr30K, Visual
Genome, and ReferIt, as well as a complementary improvement (above 7%) over the
detector-based approaches for WSG.
article_processing_charge: No
arxiv: 1
author:
- first_name: Assaf
full_name: Arbelle, Assaf
last_name: Arbelle
- first_name: Sivan
full_name: Doveh, Sivan
last_name: Doveh
- first_name: Amit
full_name: Alfassy, Amit
last_name: Alfassy
- first_name: Joseph
full_name: Shtok, Joseph
last_name: Shtok
- first_name: Guy
full_name: Lev, Guy
last_name: Lev
- first_name: Eli
full_name: Schwartz, Eli
last_name: Schwartz
- first_name: Hilde
full_name: Kuehne, Hilde
last_name: Kuehne
- first_name: Hila Barak
full_name: Levi, Hila Barak
last_name: Levi
- first_name: Prasanna
full_name: Sattigeri, Prasanna
last_name: Sattigeri
- first_name: Rameswar
full_name: Panda, Rameswar
last_name: Panda
- first_name: Chun-Fu
full_name: Chen, Chun-Fu
last_name: Chen
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Kate
full_name: Saenko, Kate
last_name: Saenko
- first_name: Shimon
full_name: Ullman, Shimon
last_name: Ullman
- first_name: Raja
full_name: Giryes, Raja
last_name: Giryes
- first_name: Rogerio
full_name: Feris, Rogerio
last_name: Feris
- first_name: Leonid
full_name: Karlinsky, Leonid
last_name: Karlinsky
citation:
ama: 'Arbelle A, Doveh S, Alfassy A, et al. Detector-free weakly supervised grounding
by separation. In: IEEE/CVF International Conference on Computer Vision.
Vol 15. Institute of Electrical and Electronics Engineers; 2021. doi:10.1109/iccv48922.2021.00182'
apa: 'Arbelle, A., Doveh, S., Alfassy, A., Shtok, J., Lev, G., Schwartz, E., … Karlinsky,
L. (2021). Detector-free weakly supervised grounding by separation. In IEEE/CVF
International Conference on Computer Vision (Vol. 15). Montreal, Canada: Institute
of Electrical and Electronics Engineers. https://doi.org/10.1109/iccv48922.2021.00182'
chicago: Arbelle, Assaf, Sivan Doveh, Amit Alfassy, Joseph Shtok, Guy Lev, Eli Schwartz,
Hilde Kuehne, et al. “Detector-Free Weakly Supervised Grounding by Separation.”
In IEEE/CVF International Conference on Computer Vision, Vol. 15. Institute
of Electrical and Electronics Engineers, 2021. https://doi.org/10.1109/iccv48922.2021.00182.
ieee: A. Arbelle et al., “Detector-free weakly supervised grounding by separation,”
in IEEE/CVF International Conference on Computer Vision, Montreal, Canada,
2021, vol. 15.
ista: 'Arbelle A, Doveh S, Alfassy A, Shtok J, Lev G, Schwartz E, Kuehne H, Levi
HB, Sattigeri P, Panda R, Chen C-F, Bronstein AM, Saenko K, Ullman S, Giryes R,
Feris R, Karlinsky L. 2021. Detector-free weakly supervised grounding by separation.
IEEE/CVF International Conference on Computer Vision. ICCV: International Conference
on Computer Vision vol. 15.'
mla: Arbelle, Assaf, et al. “Detector-Free Weakly Supervised Grounding by Separation.”
IEEE/CVF International Conference on Computer Vision, vol. 15, Institute
of Electrical and Electronics Engineers, 2021, doi:10.1109/iccv48922.2021.00182.
short: A. Arbelle, S. Doveh, A. Alfassy, J. Shtok, G. Lev, E. Schwartz, H. Kuehne,
H.B. Levi, P. Sattigeri, R. Panda, C.-F. Chen, A.M. Bronstein, K. Saenko, S. Ullman,
R. Giryes, R. Feris, L. Karlinsky, in:, IEEE/CVF International Conference on Computer
Vision, Institute of Electrical and Electronics Engineers, 2021.
conference:
end_date: 2021-10-17
location: Montreal, Canada
name: 'ICCV: International Conference on Computer Vision'
start_date: 2021-10-10
date_created: 2024-10-08T13:02:34Z
date_published: 2021-10-20T00:00:00Z
date_updated: 2024-10-15T08:22:47Z
day: '20'
doi: 10.1109/iccv48922.2021.00182
extern: '1'
external_id:
arxiv:
- '2104.09829'
intvolume: ' 15'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.2104.09829
month: '10'
oa: 1
oa_version: Preprint
publication: IEEE/CVF International Conference on Computer Vision
publication_identifier:
eisbn:
- '9781665428125'
publication_status: published
publisher: Institute of Electrical and Electronics Engineers
quality_controlled: '1'
scopus_import: '1'
status: public
title: Detector-free weakly supervised grounding by separation
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 15
year: '2021'
...
---
OA_place: repository
OA_type: green
_id: '18240'
abstract:
- lang: eng
text: Mechanical image stabilization using actuated gimbals enables capturing long-exposure
shots without suffering from blur due to camera motion. These devices, however,
are often physically cumbersome and expensive, limiting their widespread use.
In this work, we propose to digitally emulate a mechanically stabilized system
from the input of a fast unstabilized camera. To exploit the trade-off between
motion blur at long exposures and low SNR at short exposures, we train a CNN that
estimates a sharp high-SNR image by aggregating a burst of noisy short-exposure
frames, related by unknown motion. We further suggest learning the burst’s exposure
times in an end-to-end manner, thus balancing the noise and blur across the frames.
We demonstrate this method’s advantage over the traditional approach of deblurring
a single image or denoising a fixed-exposure burst on both synthetic and real
data.
article_processing_charge: No
arxiv: 1
author:
- first_name: Omer
full_name: Dahary, Omer
last_name: Dahary
- first_name: Matan
full_name: Jacoby, Matan
last_name: Jacoby
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
citation:
ama: 'Dahary O, Jacoby M, Bronstein AM. Digital gimbal: End-to-end deep image stabilization
with learnable exposure times. In: IEEE/CVF Conference on Computer Vision and
Pattern Recognition. Vol 38. Institute of Electrical and Electronics Engineers;
2021. doi:10.1109/cvpr46437.2021.01176'
apa: 'Dahary, O., Jacoby, M., & Bronstein, A. M. (2021). Digital gimbal: End-to-end
deep image stabilization with learnable exposure times. In IEEE/CVF Conference
on Computer Vision and Pattern Recognition (Vol. 38). Nashville, TN, United
States: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/cvpr46437.2021.01176'
chicago: 'Dahary, Omer, Matan Jacoby, and Alex M. Bronstein. “Digital Gimbal: End-to-End
Deep Image Stabilization with Learnable Exposure Times.” In IEEE/CVF Conference
on Computer Vision and Pattern Recognition, Vol. 38. Institute of Electrical
and Electronics Engineers, 2021. https://doi.org/10.1109/cvpr46437.2021.01176.'
ieee: 'O. Dahary, M. Jacoby, and A. M. Bronstein, “Digital gimbal: End-to-end deep
image stabilization with learnable exposure times,” in IEEE/CVF Conference
on Computer Vision and Pattern Recognition, Nashville, TN, United States,
2021, vol. 38.'
ista: 'Dahary O, Jacoby M, Bronstein AM. 2021. Digital gimbal: End-to-end deep image
stabilization with learnable exposure times. IEEE/CVF Conference on Computer Vision
and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition
vol. 38.'
mla: 'Dahary, Omer, et al. “Digital Gimbal: End-to-End Deep Image Stabilization
with Learnable Exposure Times.” IEEE/CVF Conference on Computer Vision and
Pattern Recognition, vol. 38, Institute of Electrical and Electronics Engineers,
2021, doi:10.1109/cvpr46437.2021.01176.'
short: O. Dahary, M. Jacoby, A.M. Bronstein, in:, IEEE/CVF Conference on Computer
Vision and Pattern Recognition, Institute of Electrical and Electronics Engineers,
2021.
conference:
end_date: 2021-06-25
location: Nashville, TN, United States
name: 'CVPR: Conference on Computer Vision and Pattern Recognition'
start_date: 2021-06-20
date_created: 2024-10-08T13:02:53Z
date_published: 2021-06-30T00:00:00Z
date_updated: 2024-10-15T08:42:37Z
day: '30'
doi: 10.1109/cvpr46437.2021.01176
extern: '1'
external_id:
arxiv:
- '2012.04515'
intvolume: ' 38'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.2012.04515
month: '06'
oa: 1
oa_version: Preprint
publication: IEEE/CVF Conference on Computer Vision and Pattern Recognition
publication_identifier:
eisbn:
- '9781665445092'
publication_status: published
publisher: Institute of Electrical and Electronics Engineers
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Digital gimbal: End-to-end deep image stabilization with learnable exposure
times'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 38
year: '2021'
...
---
OA_place: repository
OA_type: green
_id: '18241'
abstract:
- lang: eng
text: Multiple-input multiple-output (MIMO) radar is one of the leading depth sensing
modalities. However, the usage of multiple receive channels lead to relative high
costs and prevent the penetration of MIMOs in many areas such as the automotive
industry. Over the last years, few studies concentrated on designing reduced measurement
schemes and image reconstruction schemes for MIMO radars, however these problems
have been so far addressed separately. On the other hand, recent works in optical
computational imaging have demonstrated growing success of simultaneous learning-based
design of the acquisition and reconstruction schemes, manifesting significant
improvement in the reconstruction quality. Inspired by these successes, in this
work, we propose to learn MIMO acquisition parameters in the form of receive (Rx)
antenna elements locations jointly with an image neural-network based reconstruction.
To this end, we propose an algorithm for training the combined acquisition-reconstruction
pipeline end-to-end in a differentiable way. We demonstrate the significance of
using our learned acquisition parameters with and without the neural-network reconstruction.
Code and datasets will be released upon publication.
article_processing_charge: No
arxiv: 1
author:
- first_name: Tomer
full_name: Weiss, Tomer
last_name: Weiss
- first_name: Nissim
full_name: Peretz, Nissim
last_name: Peretz
- first_name: Sanketh
full_name: Vedula, Sanketh
last_name: Vedula
- first_name: Arie
full_name: Feuer, Arie
last_name: Feuer
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
citation:
ama: 'Weiss T, Peretz N, Vedula S, Feuer A, Bronstein AM. Joint optimization of
system design and reconstruction in MIMO radar imaging. In: 31st International
Workshop on Machine Learning for Signal Processing. Vol 4. Institute of Electrical
and Electronics Engineers; 2021. doi:10.1109/mlsp52302.2021.9596168'
apa: 'Weiss, T., Peretz, N., Vedula, S., Feuer, A., & Bronstein, A. M. (2021).
Joint optimization of system design and reconstruction in MIMO radar imaging.
In 31st International Workshop on Machine Learning for Signal Processing
(Vol. 4). Gold Coast, Australia: Institute of Electrical and Electronics Engineers.
https://doi.org/10.1109/mlsp52302.2021.9596168'
chicago: Weiss, Tomer, Nissim Peretz, Sanketh Vedula, Arie Feuer, and Alex M. Bronstein.
“Joint Optimization of System Design and Reconstruction in MIMO Radar Imaging.”
In 31st International Workshop on Machine Learning for Signal Processing,
Vol. 4. Institute of Electrical and Electronics Engineers, 2021. https://doi.org/10.1109/mlsp52302.2021.9596168.
ieee: T. Weiss, N. Peretz, S. Vedula, A. Feuer, and A. M. Bronstein, “Joint optimization
of system design and reconstruction in MIMO radar imaging,” in 31st International
Workshop on Machine Learning for Signal Processing, Gold Coast, Australia,
2021, vol. 4.
ista: 'Weiss T, Peretz N, Vedula S, Feuer A, Bronstein AM. 2021. Joint optimization
of system design and reconstruction in MIMO radar imaging. 31st International
Workshop on Machine Learning for Signal Processing. MLSP: Machine Learning for
Signal Processing vol. 4.'
mla: Weiss, Tomer, et al. “Joint Optimization of System Design and Reconstruction
in MIMO Radar Imaging.” 31st International Workshop on Machine Learning for
Signal Processing, vol. 4, Institute of Electrical and Electronics Engineers,
2021, doi:10.1109/mlsp52302.2021.9596168.
short: T. Weiss, N. Peretz, S. Vedula, A. Feuer, A.M. Bronstein, in:, 31st International
Workshop on Machine Learning for Signal Processing, Institute of Electrical and
Electronics Engineers, 2021.
conference:
end_date: 2021-10-28
location: Gold Coast, Australia
name: 'MLSP: Machine Learning for Signal Processing'
start_date: 2021-10-25
date_created: 2024-10-08T13:03:09Z
date_published: 2021-10-01T00:00:00Z
date_updated: 2024-10-16T09:41:11Z
day: '01'
doi: 10.1109/mlsp52302.2021.9596168
extern: '1'
external_id:
arxiv:
- '2110.03218'
intvolume: ' 4'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.2110.03218
month: '10'
oa: 1
oa_version: Preprint
publication: 31st International Workshop on Machine Learning for Signal Processing
publication_identifier:
eisbn:
- '9781728163383'
publication_status: published
publisher: Institute of Electrical and Electronics Engineers
quality_controlled: '1'
scopus_import: '1'
status: public
title: Joint optimization of system design and reconstruction in MIMO radar imaging
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 4
year: '2021'
...