← Search

Dominic Zhao

2 accepted papers

2022

A contrastive rule for meta-learning

NeurIPS 2022accept

Humans and other animals are capable of improving their learning performance as they solve related tasks from a given problem domain, to the point of being able to learn from extremely limited data. While synaptic plasticity is generically thought to underlie learning in the brain, the precise neura…

2021

Learning where to learn: Gradient sparsity in meta and continual learning

NeurIPS 2021poster

Finding neural network weights that generalize well from small datasets is difficult. A promising approach is to learn a weight initialization such that a small number of weight changes results in low generalization error. We show that this form of meta-learning can be improved by letting the learni…