DeepAI AI Chat
Log In Sign Up

People infer recursive visual concepts from just a few examples

by   Brenden M. Lake, et al.

Machine learning has made major advances in categorizing objects in images, yet the best algorithms miss important aspects of how people learn and think about categories. People can learn richer concepts from fewer examples, including causal models that explain how members of a category are formed. Here, we explore the limits of this human ability to infer causal "programs" -- latent generating processes with nontrivial algorithmic properties -- from one, two, or three visual examples. People were asked to extrapolate the programs in several ways, for both classifying and generating new examples. As a theory of these inductive abilities, we present a Bayesian program learning model that searches the space of programs for the best explanation of the observations. Although variable, people's judgments are broadly consistent with the model and inconsistent with several alternatives, including a pre-trained deep neural network for object recognition, indicating that people can learn and reason with rich algorithmic abstractions from sparse input data.


page 1

page 2

page 3

page 4


Compositional diversity in visual concept learning

Humans leverage compositionality to efficiently learn new concepts, unde...

Human few-shot learning of compositional instructions

People learn in fast and flexible ways that have not been emulated by ma...

Flexible Compositional Learning of Structured Visual Concepts

Humans are highly efficient learners, with the ability to grasp the mean...

From Perception to Programs: Regularize, Overparameterize, and Amortize

Toward combining inductive reasoning with perception abilities, we devel...

Beyond Object Recognition: A New Benchmark towards Object Concept Learning

Understanding objects is a central building block of artificial intellig...

Identifying concept libraries from language about object structure

Our understanding of the visual world goes beyond naming objects, encomp...

Actively learning to learn causal relationships

How do people actively learn to learn? That is, how and when do people c...