Timezone: »

 
Poster
Local plasticity rules can learn deep representations using self-supervised contrastive predictions
Bernd Illing · Jean Ventura · Guillaume Bellec · Wulfram Gerstner

Wed Dec 08 04:30 PM -- 06:00 PM (PST) @
in Poster Session 4 »

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.

Keywords: Deep Learning · Neuroscience · Self-Supervised Learning

Author Information

Bernd Illing (EPFL)
Jean Ventura (Swiss Federal Institute of Technology Lausanne)
Guillaume Bellec (Graz University of Technology)
Wulfram Gerstner (EPFL)

More from the Same Authors