Brenden M. Lake

research

∙ 07/06/2021

Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning

Human reasoning can often be understood as an interplay between two syst...

Maxwell Nye, et al. ∙

research

∙ 05/20/2021

Flexible Compositional Learning of Structured Visual Concepts

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

Yanli Zhou, et al. ∙

research

∙ 03/10/2021

Fast and flexible: Human program induction in abstract reasoning tasks

The Abstraction and Reasoning Corpus (ARC) is a challenging program indu...

Aysja Johnson, et al. ∙

research

∙ 02/23/2021

Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others

To achieve human-like common sense about everyday life, machine learning...

Kanishk Gandhi, et al. ∙

research

∙ 08/04/2020

Word meaning in minds and machines

Machines show an increasingly broad set of linguistic competencies, than...

Brenden M. Lake, et al. ∙

research

∙ 07/31/2020

Self-supervised learning through the eyes of a child

Within months of birth, children have meaningful expectations about the ...

A. Emin Orhan, et al. ∙

research

∙ 06/25/2020

Learning Task-General Representations with Generative Neuro-Symbolic Modeling

A hallmark of human intelligence is the ability to interact directly wit...

Reuben Feinman, et al. ∙

research

∙ 03/19/2020

Generating new concepts with hybrid neuro-symbolic models

Human conceptual knowledge supports the ability to generate novel yet hi...

Reuben Feinman, et al. ∙

research

∙ 03/12/2020

Learning word-referent mappings and concepts from raw inputs

How do children learn correspondences between the language and the world...

Wai Keen Vong, et al. ∙

research

∙ 03/12/2020

Learning Compositional Rules via Neural Program Synthesis

Many aspects of human reasoning, including language, require learning ru...

Maxwell I. Nye, et al. ∙

research

∙ 03/11/2020

A Benchmark for Systematic Generalization in Grounded Language Understanding

Human language users easily interpret expressions that describe unfamili...

Laura Ruis, et al. ∙

research

∙ 02/16/2020

Investigating Simple Object Representations in Model-Free Deep Reinforcement Learning

We explore the benefits of augmenting state-of-the-art model-free deep r...

Guy Davidson, et al. ∙

research

∙ 07/23/2019

Modeling question asking using neural program generation

People ask questions that are far richer, more informative, and more cre...

ZiYun Wang, et al. ∙

research

∙ 06/24/2019

Mutual exclusivity as a challenge for neural networks

Strong inductive biases allow children to learn in fast and adaptable wa...

Kanishk Gandhi, et al. ∙

research

∙ 06/20/2019

Improving the robustness of ImageNet classifiers using elements of human visual cognition

We investigate the robustness properties of image recognition models equ...

A. Emin Orhan, et al. ∙

research

∙ 06/12/2019

Compositional generalization through meta sequence-to-sequence learning

People can learn a new concept and use it compositionally, understanding...

Brenden M. Lake, et al. ∙

research

∙ 04/17/2019

People infer recursive visual concepts from just a few examples

Machine learning has made major advances in categorizing objects in imag...

Brenden M. Lake, et al. ∙

research

∙ 03/05/2019

Learning a smooth kernel regularizer for convolutional neural networks

Modern deep neural networks require a tremendous amount of data to train...

Reuben Feinman, et al. ∙

research

∙ 02/09/2019

The Omniglot Challenge: A 3-Year Progress Report

Three years ago, we released the Omniglot dataset for developing more hu...

Brenden M. Lake, et al. ∙

research

∙ 01/14/2019

Human few-shot learning of compositional instructions

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

Brenden M. Lake, et al. ∙

research

∙ 07/19/2018

Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks

Systematic compositionality is the ability to recombine meaningful units...

João Loula, et al. ∙

research

∙ 02/08/2018

Learning Inductive Biases with Simple Neural Networks

People use rich prior knowledge about the world in order to efficiently ...

Reuben Feinman, et al. ∙

research

∙ 11/16/2017

Question Asking as Program Generation

A hallmark of human intelligence is the ability to ask rich, creative, a...

Anselm Rothe, et al. ∙

research

∙ 10/31/2017

Still not systematic after all these years: On the compositional skills of sequence-to-sequence recurrent networks

Humans can understand and produce new utterances effortlessly, thanks to...

Brenden M. Lake, et al. ∙

research

∙ 04/01/2016

Building Machines That Learn and Think Like People

Recent progress in artificial intelligence (AI) has renewed interest in ...

Brenden M. Lake, et al. ∙

Brenden M. Lake

Featured Co-authors

Ruslan Salakhutdinov

Joshua B. Tenenbaum

Marco Baroni

Tal Linzen

Jacob Andreas

Armando Solar-Lezama

ZiYun Wang

Diane Bouchacourt

Samuel J. Gershman

Maxwell Nye

A. Emin Orhan

Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning

Flexible Compositional Learning of Structured Visual Concepts

Fast and flexible: Human program induction in abstract reasoning tasks

Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others

Word meaning in minds and machines

Self-supervised learning through the eyes of a child

Learning Task-General Representations with Generative Neuro-Symbolic Modeling

Generating new concepts with hybrid neuro-symbolic models

Learning word-referent mappings and concepts from raw inputs

Learning Compositional Rules via Neural Program Synthesis

A Benchmark for Systematic Generalization in Grounded Language Understanding

Investigating Simple Object Representations in Model-Free Deep Reinforcement Learning

Modeling question asking using neural program generation

Mutual exclusivity as a challenge for neural networks

Improving the robustness of ImageNet classifiers using elements of human visual cognition

Compositional generalization through meta sequence-to-sequence learning

People infer recursive visual concepts from just a few examples

Learning a smooth kernel regularizer for convolutional neural networks

The Omniglot Challenge: A 3-Year Progress Report

Human few-shot learning of compositional instructions

Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks

Learning Inductive Biases with Simple Neural Networks

Question Asking as Program Generation

Still not systematic after all these years: On the compositional skills of sequence-to-sequence recurrent networks

Building Machines That Learn and Think Like People