decolle-snn-learning
CommunityEnd-to-end online learning for spiking nets.
Education & Research#neural-networks#snn#online-learning#decolle#spiking-neurons#synthetic-gradients
Authorhiyenwong
Version1.0.0
Installs0
System Documentation
What problem does it solve?
DECOLLE enables end-to-end online training of spiking neural networks using locally computed synthetic gradients, reducing reliance on full backpropagation across time.
Core Features & Use Cases
- Local, layer-wise learning with synthetic gradients for deep SNNs.
- Real-time online learning and adaptation for neuromorphic systems.
- Suitable for research and experiments in event-driven vision and online learning.
Quick Start
Provide a spike-encoded input sequence to the DECOLLE network and run one training step to observe local and final losses.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: decolle-snn-learning Download link: https://github.com/hiyenwong/ai_collection/archive/main.zip#decolle-snn-learning Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.