← Search

Sreejan Kumar

2 accepted papers

2022

Using natural language and program abstractions to instill human inductive biases in machines

NeurIPS 2022accept

Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning may sometimes acquire very different strategies from humans. We show that co-train…

2021

Meta-Learning of Structured Task Distributions in Humans and Machines

ICLR 2021poster

In recent years, meta-learning, in which a model is trained on a family of tasks (i.e. a task distribution), has emerged as an approach to training neural networks to perform tasks that were previously assumed to require structured representations, making strides toward closing the gap between human…