Skip to yearly menu bar Skip to main content


Oral Poster

Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language

Kevin Ellis

Great Hall & Hall B1+B2 (level 1) #2015
[ ]
[ Paper]  [ Poster]  [ OpenReview] 
Wed 13 Dec 8:45 a.m. PST — 10:45 a.m. PST
 
Oral presentation: Oral 3A Neuro
Wed 13 Dec 8 a.m. PST — 8:45 a.m. PST

Abstract:

A core tension in models of concept learning is that the model must carefully balance the tractability of inference against the expressivity of the hypothesis class. Humans, however, can efficiently learn a broad range of concepts. We introduce a model of inductive learning that seeks to be human-like in that sense.It implements a Bayesian reasoning process where a language model first proposes candidate hypotheses expressed in natural language, which are then re-weighed by a prior and a likelihood.By estimating the prior from human data, we can predict human judgments on learning problems involving numbers and sets, spanning concepts that are generative, discriminative, propositional, and higher-order.

Chat is not available.