no code implementations • 1 Jan 2021 • Rares C Cristian, Max Dabagia, Christos Papadimitriou, Santosh Vempala
Here we hypothesize that (a) Brains employ synaptic plasticity rules that serve as proxies for GD; (b) These rules themselves can be learned by GD on the rule parameters; and (c) This process may be a missing ingredient for the development of ANNs that generalize well and are robust to adversarial perturbations.
