Superconducting optoelectronic circuits for neuromorphic computing

JM Shainline, SM Buckley, RP Mirin, SW Nam - Physical Review Applied, 2017 - APS
Neural networks have proven effective for solving many difficult computational problems, yet
implementing complex neural networks in software is computationally expensive. To explore …

Energy-efficient time-domain vector-by-matrix multiplier for neurocomputing and beyond

M Bavandpour, MR Mahmoodi… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
We propose an extremely energy-efficient mixed-signal N× N vector-by-matrix multiplication
(VMM) in a time domain. Multi-bit inputs/outputs are represented with time-encoded digital …

Towards ultra-high performance and energy efficiency of deep learning systems: an algorithm-hardware co-optimization framework

Y Wang, C Ding, Z Li, G Yuan, S Liao, X Ma… - Proceedings of the …, 2018 - ojs.aaai.org
Hardware accelerations of deep learning systems have been extensively investigated in
industry and academia. The aim of this paper is to achieve ultra-high energy efficiency and …

Memristor-based perceptron classifier: Increasing complexity and co** with imperfect hardware

FM Bayat, M Prezioso, B Chakrabarti… - 2017 IEEE/ACM …, 2017 - ieeexplore.ieee.org
We experimentally demonstrate classification of 4× 4 binary images into 4 classes, using a 3-
layer mixed-signal neuromorphic network (“MLP perceptron”), based on two passive 20× 20 …

Weight programming in DNN analog hardware accelerators in the presence of NVM variability

C Mackin, H Tsai, S Ambrogio… - Advanced Electronic …, 2019 - Wiley Online Library
Crossbar arrays of nonvolatile memory (NVM) can potentially accelerate development of
deep neural networks (DNNs) by implementing crucial multiply–accumulate (MAC) …

Neuromorphic computing with phase change, device reliability, and variability challenges

C Mackin, P Narayanan, S Ambrogio… - 2020 IEEE …, 2020 - ieeexplore.ieee.org
Neuromorphic computing with analog memory can accelerate deep neural networks (DNNs)
by enabling multiply-accumulate (MAC) operations to occur within memory. Analog memory …

Exponential-weight multilayer perceptron

FM Bayat, X Guo, D Strukov - 2017 International Joint …, 2017 - ieeexplore.ieee.org
Analog integrated circuits may increase the neuromorphic network performance
dramatically, leaving far behind their digital and biological counterparts, while approaching …

[PDF][PDF] 180-nm NOR-Flash Mixed-Signal Neuromorphic Image Classifier: Chip-to-Chip Statistics, Retention, and Temperature Sensitivity

X Guo, F Merrikh-Bayat, M Prezioso, DB Strukov - Target - ece.ucsb.edu
Mixed-signal neuromorphic circuits based on analog nonvolatile memory devices may far
surpass their digital counterparts in performance and energy efficiency. Recently, we have …