Superconducting optoelectronic circuits for neuromorphic computing
Neural networks have proven effective for solving many difficult computational problems, yet
implementing complex neural networks in software is computationally expensive. To explore …
implementing complex neural networks in software is computationally expensive. To explore …
Energy-efficient time-domain vector-by-matrix multiplier for neurocomputing and beyond
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 …
(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
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 …
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
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 …
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
Crossbar arrays of nonvolatile memory (NVM) can potentially accelerate development of
deep neural networks (DNNs) by implementing crucial multiply–accumulate (MAC) …
deep neural networks (DNNs) by implementing crucial multiply–accumulate (MAC) …
Neuromorphic computing with phase change, device reliability, and variability challenges
Neuromorphic computing with analog memory can accelerate deep neural networks (DNNs)
by enabling multiply-accumulate (MAC) operations to occur within memory. Analog memory …
by enabling multiply-accumulate (MAC) operations to occur within memory. Analog memory …
Exponential-weight multilayer perceptron
Analog integrated circuits may increase the neuromorphic network performance
dramatically, leaving far behind their digital and biological counterparts, while approaching …
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
Mixed-signal neuromorphic circuits based on analog nonvolatile memory devices may far
surpass their digital counterparts in performance and energy efficiency. Recently, we have …
surpass their digital counterparts in performance and energy efficiency. Recently, we have …