---
res:
  bibo_abstract:
  - Neural-network classifiers achieve high accuracy when predicting the class of
    an input that they were trained to identify. Maintaining this accuracy in dynamic
    environments, where inputs frequently fall outside the fixed set of initially
    known classes, remains a challenge. We consider the problem of monitoring the
    classification decisions of neural networks in the presence of novel classes.
    For this purpose, we generalize our recently proposed abstraction-based monitor
    from binary output to real-valued quantitative output. This quantitative output
    enables new applications, two of which we investigate in the paper. As our first
    application, we introduce an algorithmic framework for active monitoring of a
    neural network, which allows us to learn new classes dynamically and yet maintain
    high monitoring performance. As our second application, we present an offline
    procedure to retrain the neural network to improve the monitor’s detection performance
    without deteriorating the network’s classification accuracy. Our experimental
    evaluation demonstrates both the benefits of our active monitoring framework in
    dynamic scenarios and the effectiveness of the retraining procedure.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Konstantin
      foaf_name: Kueffner, Konstantin
      foaf_surname: Kueffner
      foaf_workInfoHomepage: http://www.librecat.org/personId=8121a2d0-dc85-11ea-9058-af578f3b4515
    orcid: 0000-0001-8974-2542
  - foaf_Person:
      foaf_givenName: Anna
      foaf_name: Lukina, Anna
      foaf_surname: Lukina
      foaf_workInfoHomepage: http://www.librecat.org/personId=CBA4D1A8-0FE8-11E9-BDE6-07BFE5697425
  - foaf_Person:
      foaf_givenName: Christian
      foaf_name: Schilling, Christian
      foaf_surname: Schilling
      foaf_workInfoHomepage: http://www.librecat.org/personId=3A2F4DCE-F248-11E8-B48F-1D18A9856A87
    orcid: 0000-0003-3658-1065
  - foaf_Person:
      foaf_givenName: Thomas A
      foaf_name: Henzinger, Thomas A
      foaf_surname: Henzinger
      foaf_workInfoHomepage: http://www.librecat.org/personId=40876CD8-F248-11E8-B48F-1D18A9856A87
    orcid: 0000-0002-2985-7724
  bibo_doi: 10.1007/s10009-023-00711-4
  bibo_volume: 25
  dct_date: 2023^xs_gYear
  dct_identifier:
  - UT:001020160000001
  dct_isPartOf:
  - http://id.crossref.org/issn/1433-2779
  - http://id.crossref.org/issn/1433-2787
  dct_language: eng
  dct_publisher: Springer Nature@
  dct_title: 'Into the unknown: Active monitoring of neural networks (extended version)@'
...