@article{21554,
  abstract     = {Recent progress in artificial intelligence is largely attributed to the rapid development of machine learning, especially in the algorithm and neural network models. However, it is the performance of the hardware, in particular the energy efficiency of a computing system that sets the fundamental limit of the capability of machine learning. Data-centric computing requires a revolution in hardware systems, since traditional digital computers based on transistors and the von Neumann architecture were not purposely designed for neuromorphic computing. A hardware platform based on emerging devices and new architecture is the hope for future computing with dramatically improved throughput and energy efficiency. Building such a system, nevertheless, faces a number of challenges, ranging from materials selection, device optimization, circuit fabrication and system integration, to name a few. The aim of this Roadmap is to present a snapshot of emerging hardware technologies that are potentially beneficial for machine learning, providing the Nanotechnology readers with a perspective of challenges and opportunities in this burgeoning field.},
  author       = {Berggren, Karl and Xia, Qiangfei and Likharev, Konstantin K and Strukov, Dmitri B and Jiang, Hao and Mikolajick, Thomas and Querlioz, Damien and Salinga, Martin and Erickson, John R and Pi, Shuang and Xiong, Feng and Lin, Peng and Li, Can and Chen, Yu and Xiong, Shisheng and Hoskins, Brian D and Daniels, Matthew W and Madhavan, Advait and Liddle, James A and McClelland, Jabez J and Yang, Yuchao and Rupp, Jennifer and Nonnenmann, Stephen S and Cheng, Kwang-Ting and Gong, Nanbo and Lastras-Montaño, Miguel Angel and Talin, A Alec and Salleo, Alberto and Shastri, Bhavin J and de Lima, Thomas Ferreira and Prucnal, Paul and Tait, Alexander N and Shen, Yichen and Meng, Huaiyu and Roques-Carmes, Charles and Cheng, Zengguang and Bhaskaran, Harish and Jariwala, Deep and Wang, Han and Shainline, Jeffrey M and Segall, Kenneth and Yang, J Joshua and Roy, Kaushik and Datta, Suman and Raychowdhury, Arijit},
  issn         = {1361-6528},
  journal      = {Nanotechnology},
  number       = {1},
  publisher    = {IOP Publishing},
  title        = {{Roadmap on emerging hardware and technology for machine learning}},
  doi          = {10.1088/1361-6528/aba70f},
  volume       = {32},
  year         = {2020},
}

@article{18028,
  abstract     = {We measure the conductance and current–voltage characteristics of two amine-terminated molecular wires— 4,4'-diaminostilbene and bis-(4-aminophenyl)acetylene—by breaking Au point contacts in a molecular solution at room temperature. Histograms compiled from thousands of measurements show a slight increase in the molecular junction conductance (I/V) as the bias is increased to nearly 450 mV. Comparatively, similar conductance measurements made with 1,6-diaminohexane, a saturated molecule, demonstrate almost no bias dependence. We also present a new technique to measure a statistically defined current–voltage (I–V) curve. Application to all three molecules shows that 4,4'-diaminostilbene exhibits the largest increase in differential conductance as a function of applied bias. This indicates that the predominant transport channel for 4,4'-diaminostilbene (the highest occupied molecular orbital) is closer to the Fermi level of the metal than that of the other molecules, consistent with the trends observed in the molecular ionization potential. We find that junctions constructed with the conjugated molecules show greater noise in individual junctions and less structural stability, on average, at biases greater than 450 mV. In contrast, junctions formed with the alkane can sustain a bias of up to 900 mV. This significantly affects the statistically averaged I–V characteristic measured for the conjugated molecules at higher bias.},
  author       = {Widawsky, J R and Kamenetska, M and Klare, J and Nuckolls, C and Steigerwald, M L and Hybertsen, M S and Venkataraman, Latha},
  issn         = {1361-6528},
  journal      = {Nanotechnology},
  number       = {43},
  publisher    = {IOP Publishing},
  title        = {{Measurement of voltage-dependent electronic transport across amine-linked single-molecular-wire junctions}},
  doi          = {10.1088/0957-4484/20/43/434009},
  volume       = {20},
  year         = {2009},
}