activity
20172024
most citedHuman few-shot learning of compositional instructions

27 citations · 66 across the 9 of their papers we have counts for

collaborators
Showing cs.AIShow all

6 papers · 1 filter

cs.AI20241 cited

H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark

Solim LeGris, Wai Keen Vong, Brenden M. Lake +1

The Abstraction and Reasoning Corpus (ARC) is a visual program synthesis benchmark designed to test challenging out-of-distribution generalization in humans and machines. Since 201…

cs.AI20224 cited

Improving Systematic Generalization Through Modularity and Augmentation

Laura Ruis, Brenden Lake

Systematic generalization is the ability to combine known parts into novel meaning; an important aspect of efficient human learning, but a weakness of neural network learning. In t…

cs.AI20205 cited

CURI: A Benchmark for Productive Concept Learning Under Uncertainty

Ramakrishna Vedantam, Arthur Szlam, Maximilian Nickel +2

Humans can learn and reason under substantial uncertainty in a space of infinitely many concepts, including structured relational concepts ("a scene with objects that have the same…

cs.AI2020

Learning Task-General Representations with Generative Neuro-Symbolic Modeling

Reuben Feinman, Brenden M. Lake

People can learn rich, general-purpose conceptual representations from only raw perceptual inputs. Current machine learning approaches fall well short of these human standards, alt…

cs.AI2020

Learning Compositional Rules via Neural Program Synthesis

Maxwell I. Nye, Armando Solar-Lezama, Joshua B. Tenenbaum +1

Many aspects of human reasoning, including language, require learning rules from very little data. Humans can do this, often learning systematic rules from very few examples, and c…

cs.AI2019

The Omniglot challenge: a 3-year progress report

Brenden M. Lake, Ruslan Salakhutdinov, Joshua B. Tenenbaum

Three years ago, we released the Omniglot dataset for one-shot learning, along with five challenge tasks and a computational model that addresses these tasks. The model was not mea…