Accurate and compact convolutional neural network based on stochastic computing
Abstract Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in
many recognition problems. However, CNN models are computation-intensive and require …
many recognition problems. However, CNN models are computation-intensive and require …
Design space exploration of neural network activation function circuits
The widespread application of artificial neural networks has prompted researchers to
experiment with field-programmable gate array and customized ASIC designs to speed up …
experiment with field-programmable gate array and customized ASIC designs to speed up …
Energy-efficient stochastic computing with superparamagnetic tunnel junctions
Superparamagnetic tunnel junctions (SMTJs) have emerged as a competitive, realistic
nanotechnology to support novel forms of stochastic computation in CMOS-compatible …
nanotechnology to support novel forms of stochastic computation in CMOS-compatible …
Accurate and efficient stochastic computing hardware for convolutional neural networks
This paper presents an efficient unipolar stochastic computing hardware for convolutional
neural networks (CNNs). It includes stochastic ReLU and optimized max function, which are …
neural networks (CNNs). It includes stochastic ReLU and optimized max function, which are …
Stochastic computing in convolutional neural network implementation: A review
YY Lee, ZA Halim - PeerJ Computer Science, 2020 - peerj.com
Stochastic computing (SC) is an alternative computing domain for ubiquitous deterministic
computing whereby a single logic gate can perform the arithmetic operation by exploiting the …
computing whereby a single logic gate can perform the arithmetic operation by exploiting the …
Spectral-based convolutional neural network without multiple spatial-frequency domain switchings
Recent researches have shown that spectral representation provides a significant speed-up
in the massive computation workload of convolution operations in the inference (feed …
in the massive computation workload of convolution operations in the inference (feed …
Architecture considerations for stochastic computing accelerators
Stochastic computing (SC) is an alternative computing technique for embedded systems
which offers lower area and power, and better error resilience compared to binary-encoded …
which offers lower area and power, and better error resilience compared to binary-encoded …
Neural network classifiers using stochastic computing with a hardware-oriented approximate activation function
Neural networks are becoming prevalent in many areas, such as pattern recognition and
medical diagnosis. Stochastic computing is one potential solution for neural networks …
medical diagnosis. Stochastic computing is one potential solution for neural networks …
Implementation of artificial neural networks using magnetoresistive random-access memory-based stochastic computing units
Hardware implementation of artificial neural networks (ANNs) using conventional binary
arithmetic units requires large area and energy, due to the massive multiplication and …
arithmetic units requires large area and energy, due to the massive multiplication and …
When sorting network meets parallel bitstreams: A fault-tolerant parallel ternary neural network accelerator based on stochastic computing
Stochastic computing (SC) has been widely used in neural networks (NNs) due to its simple
hardware cost and high fault tolerance. Conventionally, SC-based NN accelerators adopt a …
hardware cost and high fault tolerance. Conventionally, SC-based NN accelerators adopt a …