Local Plasticity Rules Can Learn Deep Representations Using Selfsupervised Contrastive Predictions

# Local plasticity rules can learn deep representations using self-supervised contrastive predictions

**arXiv ID:** 2010.08262
**Authors:** Bernd Illing, Jean Ventura, Guillaume Bellec, Wulfram Gerstner
**Published:** 2020-10-16T09:32:35Z
**Abstract:**
Learning in the brain is poorly understood and learning rules that respect biological constraints, yet yield deep hierarchical representations, are still unknown. Here, we propose a learning rule that takes inspiration from neuroscience and recent advances in self-supervised deep learning. Learning minimizes a simple layer-specific loss function and does not need to back-propagate error signals within or between layers. Instead, weight updates follow a local, Hebbian, learning rule that only depends on pre- and post-synaptic neuronal activity, predictive dendritic input and widely broadcasted modulation factors which are identical for large groups of neurons. The learning rule applies contrastive predictive learning to a causal, biological setting using saccades (i.e. rapid shifts in gaze direction). We find that networks trained with this self-supervised and local rule build deep hierarchical representations of images, speech and video.

## Skill Description

This skill is generated from the arXiv paper: Local plasticity rules can learn deep representations using self-supervised contrastive predictions (2010.08262).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2010.08262](http://arxiv.org/abs/2010.08262v5)