Local Plasticity Rules Can Learn Deep Representations Using Selfsupervised Contrastive Predictions
ASecurity**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 functio...
- 3 stars
- 0 votes
- 0 copies
- 4 views
- Added September 11, 2026
Works with
Security analysis
100/100npx -y skills add hiyenwong/ai_collection --skill local-plasticity-rules-can-learn-deep-representations-using-selfsupervised-contrastive-predictions --agent claude-codeAre you the author of Local Plasticity Rules Can Learn Deep Representations Using Selfsupervised Contrastive Predictions?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-local-plasticity-rules-can-learn-deep-representati)# 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)
Attribution
Related skills
View all in tools →Comments
Loading comments…
Newsletter
Get the weekly list of safe new skills, and the ones we pulled.