Mila > Publication > Bridging the Gap Between Deep Learning and Neuroscience > Towards deep learning with spiking neurons in energy based models with contrastive Hebbian plasticity

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

Bridging the Gap Between Deep Learning and Neuroscience
Oct 2017

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

Oct 2017

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.

Reference

Linked Profiles