Towards deep learning with spiking neurons in energy based models with contrastive Hebbian plasticity
This work addresses the problem of biologically plausible learning for neuroscience and neuromorphic computing, though it appears incremental as it builds on prior rate neuron models.
The authors tackled the biological implausibility of backpropagation in deep learning by extending energy-based models with local contrastive Hebbian learning to spiking neurons, achieving preliminary success in learning a non-linear regression task with hidden layers.
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.