Local plasticity rules can learn deep representations using self-supervised contrastive predictions
arXiv:2010.08262
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.
References in corpus (9)
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Data-Efficient Image Recognition with Contrastive Predictive Coding
- Demonstrating Advantages of Neuromorphic Computation: A Pilot Study
- Training Neural Networks with Local Error Signals
- Putting An End to End-to-End: Gradient-Isolated Learning of Representations
- Why do similarity matching objectives lead to Hebbian/anti-Hebbian networks?
- Two Routes to Scalable Credit Assignment without Weight Symmetry
- LoCo: Local Contrastive Representation Learning
- A biologically plausible neural network for local supervision in cortical microcircuits