pith. sign in

arxiv: 1612.03214 · v1 · pith:UFK7GPRKnew · submitted 2016-12-09 · 💻 cs.LG · cs.NE· q-bio.NC

Towards deep learning with spiking neurons in energy based models with contrastive Hebbian plasticity

classification 💻 cs.LG cs.NEq-bio.NC
keywords learningneuronsdeepnetworksplasticitybeencontrastivehebbian
0
0 comments X
read the original abstract

In machine learning, error back-propagation in multi-layer neural networks (deep learning) has been impressively successful in supervised and reinforcement learning tasks. As a model for learning in the brain, however, deep learning has long been regarded as implausible, since it relies in its basic form on a non-local plasticity rule. To overcome this problem, energy-based models with local contrastive Hebbian learning were proposed and tested on a classification task with networks of rate neurons. We extended this work by implementing and testing such a model with networks of leaky integrate-and-fire neurons. Preliminary results indicate that it is possible to learn a non-linear regression task with hidden layers, spiking neurons and a local synaptic plasticity rule.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.