Analog Spike-Timing-Dependent Resistive Crossbar Design for Brain Inspired Computing

Zhao, Chao; Hamedani, Kian; Li, Jialing; Yi, Yang

doi:10.1109/jetcas.2017.2765892

Cited by 18 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, the STDP principle is applied to build an ISI spike decoder that could significantly improve the performance of the design in [9][10][11][12], i.e. the working frequency could be much higher than 100KHz.…”

Section: Isi Decoding Methodologymentioning

confidence: 99%

“…spike rate code, spike latency code, to serve as information carrier in their designs [7,8]. For the spike-based ISI encoding technique, two types of the analog ISI encoder and one high sampling rate decoder are introduced in [6] [9]. However, among these implementations, there are many unsolved problems that need to be seriously considered, which are high error rate, low noise immunity, low speed limitation, limited scaling up capability, low reliability, and high power consumption.…”

Section: Fig 1 Spike Processing Schemesmentioning

confidence: 99%

“…However, among these implementations, there are many unsolved problems that need to be seriously considered, which are high error rate, low noise immunity, low speed limitation, limited scaling up capability, low reliability, and high power consumption. In the existing work [6][7][8][9][10], the error rate of the designs could reach to 0.1; the spike firing frequency is required to be less than 100KHz when STDP principle is adopted; and the scaling up ability is limited due to their design architectures [6][7][8][9][10].…”

Section: Fig 1 Spike Processing Schemesmentioning

confidence: 99%

See 2 more Smart Citations

Design and Analysis of Real Time Spiking Neural Network Decoder for Neuromorphic Chips

Zhao

Liu

2019

Proceedings of the International Conference on Neuromorphic Systems

Self Cite

View full text Add to dashboard Cite

Neuromorphic computing, which is based on non-traditional architectures that mimic bio-neurological process, could offer potentially disruptive capabilities and high energy-efficiency in real-time data monitoring and prediction, and resource allocation. The first step for de-signing neuromorphic chips is to explore effective design methodologies for real time and energy efficient spiking neural network (SNN) encoders and decoders. In this paper, a spike timing dependent plasticity principle (STDP) based decoder is designed and optimized. As shown in our experimental results, the proposed STDP based SNN decoder achieves good performance in information recovery with multiple scales.

show abstract

Section: Isi Decoding Methodologymentioning

confidence: 99%

Section: Fig 1 Spike Processing Schemesmentioning

confidence: 99%

Section: Fig 1 Spike Processing Schemesmentioning

confidence: 99%

See 1 more Smart Citation

Design and Analysis of Real Time Spiking Neural Network Decoder for Neuromorphic Chips

Zhao

Liu

2019

Proceedings of the International Conference on Neuromorphic Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, an increasing number of researchers have started to implement neuromorphic computing using analog integrated circuits [46,47,49,50,71,[73][74][75][76][77][78][79]. Compared to digital implementation, analog implementation of neuromorphic computing is more energy efficient.…”

Section: Recent Progress In Neuromorphic Computingmentioning

confidence: 99%

Quantized Neural Networks and Neuromorphic Computing for Embedded Systems

Liu¹,

Yi²

2020

Intelligent System and Computing

Self Cite

View full text Add to dashboard Cite

Deep learning techniques have made great success in areas such as computer vision, speech recognition and natural language processing. Those breakthroughs made by deep learning techniques are changing every aspect of our lives. However, deep learning techniques have not realized their full potential in embedded systems such as mobiles, vehicles etc. because the high performance of deep learning techniques comes at the cost of high computation resource and energy consumption. Therefore, it is very challenging to deploy deep learning models in embedded systems because such systems have very limited computation resources and power constraints. Extensive research on deploying deep learning techniques in embedded systems has been conducted and considerable progress has been made. In this book chapter, we are going to introduce two approaches. The first approach is model compression, which is one of the very popular approaches proposed in recent years. Another approach is neuromorphic computing, which is a novel computing system that mimicks the human brain.

show abstract

“…TrueNorth chip consumes only 70 milliWatts (mW) to run 1 million spiking neurons with 256 million synapses [13][14][15]. The energy efficiency of spiking neural networks (SNNs) makes them a suitable choice for hardware implementations of artificial neurons as well [16,17].…”

Section: Introductionmentioning

confidence: 99%

The Novel Applications of Deep Reservoir Computing in Cyber-Security and Wireless Communication

Hamedani¹,

Zhou²,

Bai³

et al. 2020

Intelligent System and Computing

Self Cite

View full text Add to dashboard Cite

This chapter introduces the novel applications of deep reservoir computing (RC) systems in cyber-security and wireless communication. The RC systems are a new class of recurrent neural networks (RNNs). Traditional RNNs are very challenging to train due to vanishing/exploding gradients. However, the RC systems are easier to train and have shown similar or even better performances compared with traditional RNNs. It is very essential to study the spatio-temporal correlations in cyber-security and wireless communication domains. Therefore, RC models are good choices to explore the spatio-temporal correlations. In this chapter, we explore the applications and performance of delayed feedback reservoirs (DFRs), and echo state networks (ESNs) in the cyber-security of smart grids and symbol detection in MIMO-OFDM systems, respectively. DFRs and ESNs are two different types of RC models. We also introduce the spiking structure of DFRs as spiking artificial neural networks are more energy efficient and biologically plausible as well.

show abstract

Analog Spike-Timing-Dependent Resistive Crossbar Design for Brain Inspired Computing

Cited by 18 publications

References 22 publications

Design and Analysis of Real Time Spiking Neural Network Decoder for Neuromorphic Chips

Design and Analysis of Real Time Spiking Neural Network Decoder for Neuromorphic Chips

Quantized Neural Networks and Neuromorphic Computing for Embedded Systems

The Novel Applications of Deep Reservoir Computing in Cyber-Security and Wireless Communication

Contact Info

Product

Resources

About