Supervised learning in Spiking Neural Networks with Limited Precision: SNN/LP

A new supervised learning algorithm, SNN/LP, is proposed for Spiking Neural Networks. This novel algorithm uses limited precision for both synaptic weights and synaptic delays; 3 bits in each case. Also a genetic algorithm is used for the supervised training. The results are comparable or better than previously published work. The results are applicable to the realization of large-scale hardware neural networks. One of the trained networks is implemented in programmable hardware.

cs.NE Computer Science Engineering

View graph Source

Paper

Similar papers

Developing a supervised training algorithm for limited precision feed-forward spiking neural networksEvangelos Stromatias2011 · arXiv.org · 7 citations In Library

lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous AgentsRachmad Vidya Wicaksana Putra, Muhammad Shafique2022 · arXiv (Cornell University) · 23 citations In Library

An STDP-Based Supervised Learning Algorithm for Spiking Neural NetworksZhan Hu, Tao Wang, Xiaolin Hu2017 · International Conference on Neural Information Processing · 13 citations In Library

Lifelike Neuromorphic Learning Networks (LNLN)Aishwarya Asesh2020 · IEEE Symposium Series on Computational Intelligence · 0 citations In Library

First Error-Based Supervised Learning Algorithm for Spiking Neural NetworksXiaoling Luo, Hong Qu, Yun Zhang et al.2019 · Frontiers in Neuroscience · 18 citations In Library

Fast and Low-Precision Learning in GPU-Accelerated Spiking Neural NetworkXueyuan She, Yun Long, S. Mukhopadhyay2019 · Design, Automation and Test in Europe · 19 citations In Library

Unsupervised Spiking Neural Network with Dynamic Learning of Inhibitory NeuronsGeunbo Yang, Won-Seok Lee, Youjung Seo et al.2023 · Italian National Conference on Sensors · 6 citations In Library

Pursing the Sparse Limitation of Spiking Deep Learning StructuresHao Cheng, Jiahang Cao, Erjia Xiao et al.2023 · arXiv.org · 1 citation In Library

Training-aware Low Precision Quantization in Spiking Neural NetworksAyan Shymyrbay, M. Fouda, A. Eltawil2022 · Asilomar Conference on Signals, Systems and Computers · 5 citations In Library

BP-based supervised learning algorithm for multilayer photonic spiking neural network and hardware implementationYahui Zhang, Shuiying Xiang, Yanan Han et al.2023 · Optics Express · 3 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal