Analog synaptic devices applied to spiking neural networks for reinforcement learning applications
- 12 May 2022
- journal article
- research article
- Published by IOP Publishing in Semiconductor Science and Technology
- Vol. 37 (7) , 075002
Abstract
In this work, we implement hardware-based spiking neural network (SNN) using the thin-film transistor (TFT)-type flash synaptic devices. A hardware-based SNN architecture with synapse arrays and integrate-and-fire (I&F) neuron circuits is presented for executing reinforcement learning (RL). Two problems were used to evaluate the applicability of the proposed hardware-based SNNs to off-chip RL: the Cart Pole balancing problem and the Rush Hour problem. The neural network was trained using a deep Q-learning algorithm. The proposed hardware-based SNNs using the synapse model with measured characteristics successfully solve the two problems and show high performance, implying that the networks are suitable for executing RL. Furthermore, the effect of variations in non-ideal synaptic devices and neurons on the performance was investigated.Keywords
This publication has 20 references indexed in Scilit:
- Signal and noise extraction from analog memory elements for neuromorphic computingNature Communications, 2018
- Demonstration of Unsupervised Learning With Spike-Timing-Dependent Plasticity Using a TFT-Type NOR Flash Memory ArrayIEEE Transactions on Electron Devices, 2018
- Neuro-Inspired Computing With Emerging Nonvolatile MemorysProceedings of the IEEE, 2018
- In situ immune response and mechanisms of cell damage in central nervous system of fatal cases microcephaly by Zika virusScientific Reports, 2018
- Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image ClassificationFrontiers in Neuroscience, 2017
- Mastering the game of Go without human knowledgeNature, 2017
- Memory and Information Processing in Neuromorphic SystemsProceedings of the IEEE, 2015
- Human-level control through deep reinforcement learningNature, 2015
- Synaptic electronics: materials, devices and applicationsNanotechnology, 2013
- Immunity to Device Variations in a Spiking Neural Network With Memristive NanodevicesIEEE Transactions on Nanotechnology, 2013