MSTDP: A More Biologically Plausible Learning

11/29/2019
by   Shiyuan Li, et al.
0

Spike-timing dependent plasticity (STDP) which observed in the brain has proven to be important in biological learning. On the other hand, artificial neural networks use a different way to learn, such as Back-Propagation or Contrastive Hebbian Learning. In this work, we propose MSTDP, a new framework that uses only STDP rules for supervised and unsupervised learning. The framework works like an auto-encoder by making each input neuron also an output neuron. It can make predictions or generate patterns in one model without additional configuration. We also brought a new iterative inference method using momentum to make the framework more efficient, which can be used in training and testing phases. Finally, we verified our framework on MNIST dataset for classification and generation task.

READ FULL TEXT

page 6

page 7

research
05/22/2022

aSTDP: A More Biologically Plausible Learning

Spike-timing dependent plasticity in biological neural networks has been...
research
11/14/2021

BioLeaF: A Bio-plausible Learning Framework for Training of Spiking Neural Networks

Our brain consists of biological neurons encoding information through ac...
research
04/08/2022

Biologically-inspired neuronal adaptation improves learning in neural networks

Since humans still outperform artificial neural networks on many tasks, ...
research
06/15/2020

Equilibrium Propagation for Complete Directed Neural Networks

Artificial neural networks, one of the most successful approaches to sup...
research
02/02/2023

Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons

Activity difference based learning algorithms-such as contrastive Hebbia...
research
11/21/2017

Variational Probability Flow for Biologically Plausible Training of Deep Neural Networks

The quest for biologically plausible deep learning is driven, not just b...
research
07/12/2021

SoftHebb: Bayesian inference in unsupervised Hebbian soft winner-take-all networks

State-of-the-art artificial neural networks (ANNs) require labelled data...

Please sign up or login with your details

Forgot password? Click here to reset