Meta-Learning through Hebbian Plasticity in Random Networks

郑重声明：原文参见标题，如有侵权，请联系作者，将会撤销发布！

34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada.

Abstract

1 Introduction

2 Related work

3 Meta-learning through Evolved Local Learning Rules

3.1 Optimization details

4 Experimental Setups

4.1 Results

5 Discussion and Future Work

6 Appendix

6.1 Network Weight Visualizations

6.2 Training efficiency

6.3 Hebbian rules

6.4 Evolving initial weights and learning rules