Incremental Neural Synthesis for Spiking Neural Networks
2022 IEEE Symposium Series on Computational Intelligence (SSCI)(2022)
摘要
We present an iterative neural synthesis approach to train Convolutional Spiking Neural Networks for classification problems. Unlike previous neural synthesis methods which pri-marily compute the neuron firing rates, our method is designed to compute multiple spikes at arbitrary timings. As such, our approach is directly applicable to spatio-temporal problems using spiking network models. In our approach, each weight update is formulated as a linear Constraint Satisfaction Problem, which can then be solved using existing numerical techniques. On the MNIST, EMNIST, and ETH-80 image classification benchmarks, our approach demonstrates competitive with other models in the literature, while requiring relatively few training samples to converge to a good solution.
更多查看译文
关键词
incremental neural synthesis,neural networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要