Evolving interpretable plasticity for spiking networks

eLife

Maximilian Schmidt¹  Walter Senn²  Jakob Jordan²  Mihai A Petrovici³ 

[1] Ascent Robotics, Tokyo, Japan;RIKEN Center for Brain Science, Tokyo, Japan;Department of Physiology, University of Bern, Bern, Switzerland;Department of Physiology, University of Bern, Bern, Switzerland;Kirchhoff-Institute for Physics, Heidelberg University, Heidelberg, Germany;

关键词: metalearning;    learning to learn;    synaptic plasticity;    spiking neuronal networks;    genetic programming;    None;   

DOI  :  10.7554/eLife.66273

来源: eLife Sciences Publications, Ltd

【 摘 要 】

Continuous adaptation allows survival in an ever-changing world. Adjustments in the synaptic coupling strength between neurons are essential for this capability, setting us apart from simpler, hard-wired organisms. How these changes can be mathematically described at the phenomenological level, as so-called ‘plasticity rules’, is essential both for understanding biological information processing and for developing cognitively performant artificial systems. We suggest an automated approach for discovering biophysically plausible plasticity rules based on the definition of task families, associated performance measures and biophysical constraints. By evolving compact symbolic expressions, we ensure the discovered plasticity rules are amenable to intuitive understanding, fundamental for successful communication and human-guided generalization. We successfully apply our approach to typical learning scenarios and discover previously unknown mechanisms for learning efficiently from rewards, recover efficient gradient-descent methods for learning from target signals, and uncover various functionally equivalent STDP-like rules with tuned homeostatic mechanisms.

【 授权许可】

CC BY