AutoHebb paper proposes self-modifying neural networks with zero-shot inference and continual learning
A new arXiv paper introduces AutoHebb, self-modifying neural networks designed to zero-shot infer in novel circumstances and support continual learning, drawing on humans' and animals' capacity to generalize.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-02 05:00 · arXiv cs.LG
AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn