Spike time displacement based error backpropagation in convolutional spiking neural networks

08/31/2021
by   Maryam Mirsadeghi, et al.
0

We recently proposed the STiDi-BP algorithm, which avoids backward recursive gradient computation, for training multi-layer spiking neural networks (SNNs) with single-spike-based temporal coding. The algorithm employs a linear approximation to compute the derivative of the spike latency with respect to the membrane potential and it uses spiking neurons with piecewise linear postsynaptic potential to reduce the computational cost and the complexity of neural processing. In this paper, we extend the STiDi-BP algorithm to employ it in deeper and convolutional architectures. The evaluation results on the image classification task based on two popular benchmarks, MNIST and Fashion-MNIST datasets with the accuracies of respectively 99.2 algorithm has been applicable in deep SNNs. Another issue we consider is the reduction of memory storage and computational cost. To do so, we consider a convolutional SNN (CSNN) with two sets of weights: real-valued weights that are updated in the backward pass and their signs, binary weights, that are employed in the feedforward process. We evaluate the binary CSNN on two datasets of MNIST and Fashion-MNIST and obtain acceptable performance with a negligible accuracy drop with respect to real-valued weights (about 0.6 drops, respectively).

READ FULL TEXT

page 8

page 9

research
07/08/2020

BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning

We recently proposed the S4NN algorithm, essentially an adaptation of ba...
research
05/21/2018

Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks

Spiking neural networks (SNNs) are positioned to enable spatio-temporal ...
research
02/28/2019

A novel method for extracting interpretable knowledge from a spiking neural classifier with time-varying synaptic weights

This paper presents a novel method for information interpretability in a...
research
07/20/2022

A Temporally and Spatially Local Spike-based Backpropagation Algorithm to Enable Training in Hardware

Spiking Neural Networks (SNNs) have emerged as a hardware efficient arch...
research
07/24/2023

Sparse-firing regularization methods for spiking neural networks with time-to-first spike coding

The training of multilayer spiking neural networks (SNNs) using the erro...
research
04/12/2021

Adaptive conversion of real-valued input into spike trains

This paper presents a biologically plausible method for converting real-...
research
06/22/2021

Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks

While backpropagation (BP) has been applied to spiking neural networks (...

Please sign up or login with your details

Forgot password? Click here to reset