Supervised Learning without Backpropagation using Spike-Timing-Dependent Plasticity for Image Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Xie, Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912229588205568
author Xie, Wei
author_facet Xie, Wei
contents This study introduces a novel supervised learning approach for spiking neural networks that does not rely on traditional backpropagation. Instead, it employs spike-timing-dependent plasticity (STDP) within a supervised framework for image recognition tasks. The effectiveness of this method is demonstrated using the MNIST dataset. The model achieves approximately 40\% learning accuracy with just 10 training stimuli, where each category is exposed to the model only once during training (one-shot learning). With larger training samples, the accuracy increases up to 87\%, maintaining negligible ambiguity. Notably, with only 10 hidden neurons, the model reaches 89\% accuracy with around 10\% ambiguity. This proposed method offers a robust and efficient alternative to traditional backpropagation-based supervised learning techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16524
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Supervised Learning without Backpropagation using Spike-Timing-Dependent Plasticity for Image Recognition
Xie, Wei
Computer Vision and Pattern Recognition
Neurons and Cognition
This study introduces a novel supervised learning approach for spiking neural networks that does not rely on traditional backpropagation. Instead, it employs spike-timing-dependent plasticity (STDP) within a supervised framework for image recognition tasks. The effectiveness of this method is demonstrated using the MNIST dataset. The model achieves approximately 40\% learning accuracy with just 10 training stimuli, where each category is exposed to the model only once during training (one-shot learning). With larger training samples, the accuracy increases up to 87\%, maintaining negligible ambiguity. Notably, with only 10 hidden neurons, the model reaches 89\% accuracy with around 10\% ambiguity. This proposed method offers a robust and efficient alternative to traditional backpropagation-based supervised learning techniques.
title Supervised Learning without Backpropagation using Spike-Timing-Dependent Plasticity for Image Recognition
topic Computer Vision and Pattern Recognition
Neurons and Cognition
url https://arxiv.org/abs/2410.16524