Brenden M. Lake

Assistant Professor of Psychology and Data Science
Department of Psychology and Center for Data Science (joint)
Department of Computer Science and Center for Neural Science (affiliate)
NYU Minds, Brains, and Machines Initiative (Co-director)
Human & Machine Learning Lab and CILVR Lab (research groups)
New York University


Contact

Email: brenden@nyu.edu
Phone: (212) 998-3059
Data Science office: 60 5th Ave., Room 610, New York, NY 10011
Psychology office: 6 Washington Place, Room 589, New York, NY 10003
Curriculum Vitae
Lab website

Interested in joining the lab? Check here for info about open positions.
Please also see this page about Computational Cognitive Science at NYU.


Research

Our lab seeks the ingredients of intelligence. We use advances in machine intelligence to better understand human intelligence, and use insights from human intelligence to develop more fruitful kinds of machine intelligence.

In our pursuits, we focus on human cognitive abilities that elude the best AI systems. While there are many to choose from, our recent projects focus on the human abilities to learn new concepts from just a few examples, learn by asking questions, learn by generating new goals, and learn by producing novel combinations of known components. Our technical focus includes meta-learning, neuro-symbolic modeling, and machine learning from a child’s headcam video to learn through their “eyes and ears.”

By studying distinctively human endeavors, there is opportunity to advance both cognitive science and data science. In cognitive science, if people have abilities beyond the reach of current algorithms, then we do not fully understand how these abilities work. In data science and AI, these abilities are important open problems that represent opportunities to reverse-engineer the human solutions. Through this approach, our work has revealed key cognitive ingredients and inductive biases that people use but are missing in contemporary machine learning. Additionally, we have incorporated these ingredients into machine learning systems, making them more powerful and human-like, while also addressing longstanding debates on the capabilities of neural network models and the necessary ingredients for learning.


Teaching

PSYCH-GA 3405.004 / DS-GS 1016 : Computational cognitive modeling (current; Spring 2024)
PSYCH-GA 2207 : Categories and Concepts (last taught Fall 2023)
PSYCH-UA 46 : Lab in Cognition and Perception (last taught Fall 2023)
PSYCH-GA 3405.001 / DS-GA 3001.014 : Advancing AI through cognitive science (last taught Spring 2019)


Selected Publications

Vong, W. K., Wang, W., Orhan, A. E., and Lake, B. M (2024). Grounded language acquisition through the eyes and ears of a single child. Science, 383(6682), 504-511. [Nature News and Views]

Orhan, A. E., and Lake, B. M. (2024). Learning high-level visual representations from a child’s perspective without strong inductive biases. Nature Machine Intelligence.

Lake, B. M. and Baroni, M. (2023). Human-like systematic generalization through a meta-learning neural network. Nature, 623, 115-121. [Supplementary Information] [Code and Data] [Data (HTML viewing)]

Lake, B. M., Ullman, T. D., Tenenbaum, J. B., and Gershman, S. J. (2017). Building machines that learn and think like people. Behavioral and Brain Sciences, 40, E253.

Lake, B. M., Salakhutdinov, R., and Tenenbaum, J. B. (2015). Human-level concept learning through probabilistic program induction. Science, 350(6266), 1332-1338. [Supporting Info.] [visual Turing tests] [Omniglot data set] [Bayesian Program Learning code]



All Publications

See below for publications by year: Preprints, 2024, 2023, 2022, 2021, 2020, 2019, 2018, 2017, 2016, 2015 and earlier. Check out our lab page for a potentially more recent list.


Preprints

Tartaglini, A. R., Feucht, S., Lepori, M. A., Vong, W. V., Lovering, C., Lake, B. M., and Pavlick, E. (2023). Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations. Preprint available on arxiv:2310.09612.

Orhan, A. E., Wang, W., Wang, A. N., Ren, M., and Lake, B. M. (2024). Self-supervised learning of video representations from a child’s perspective. Preprint available on arxiv:2402.00300.

Kumar, S., Marjieh, R., Zhang, B., Campbell, D., Hu, M. Y., Bhatt, U., Lake, B. M., and Griffiths, T. (2024). Comparing Abstraction in Humans and Machines Using Multimodal Serial Reproduction. Preprint available on arxiv:2402.00300.

Zhou, Y., Lake, B. M., and Williams, A. (2024). Compositional learning of functions in humans and machines.

Qin, Y., Wang, W., and Lake, B. M. (2024). A systematic investigation of learnability from single child linguistic input. Preprint available on arxiv:2402.07899.

Leong, C. and Lake, B. M. (2024). Prompting invokes expert-like downward shifts in GPT-4V’s conceptual hierarchies.

Luo, K., Zhang, B., Xiao, Y., and Lake, B. M. (2024). Finding Unsupervised Alignment of Conceptual Systems in Image-Word Representations.

Li, W., Yasuda, S. C., Dillon, M. R., and Lake, B. M. (2024). A Machine Social Reasoning Benchmark Inspired by Infant Cognition. Preprint available on PsyArXiv:zf5nh.


2024

Vong, W. K., Wang, W., Orhan, A. E., and Lake, B. M (2024). Grounded language acquisition through the eyes and ears of a single child. Science, 383(6682), 504-511. [Nature News and Views]

Orhan, A. E., and Lake, B. M. (2024). Learning high-level visual representations from a child’s perspective without strong inductive biases. Nature Machine Intelligence.

Davidson, G., Orhan, A. E., and Lake, B. M. (2024). Spatial Relation Categorization in Infants and Deep Neural Networks. Cognition, 245, 105690.

Zhou, Y., Feinman, R., and Lake, B. M. (2024). Compositional diversity in visual concept learning. Cognition, 244, 105711.


2023

Lake, B. M. and Baroni, M. (2023). Human-like systematic generalization through a meta-learning neural network. Nature, 623, 115-121. [Supplementary Information] [Code and Data] [Data (HTML viewing)]

Wang, W., Vong, W. K., Kim, N., and Lake, B. M. (2023). Finding Structure in One Child’s Linguistic Experience. Cognitive Science, 47, e13305. [Appendix]

Lake, B. M. and Murphy, G. L. (2023). Word meaning in minds and machines. Psychological Review, 130, 401-431.

Stojnic, G., Gandhi, K., Yasuda, S., Lake, B. M., and Dillon, M. R. (2023). Commonsense Psychology in Human Infants and Machines. Cognition, 235, 105406.


2022

Vong, W. K. and Lake, B. M. (2022). Cross-situational word learning with multimodal neural networks. Cognitive Science, 46, e13122.

Tartaglini, A. R., Vong, W. K., and Lake, B. M. (2022). A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines. In Proceedings of the 44th Annual Conference of the Cognitive Science Society. [Dataset]

Davidson, G., Gureckis, T. M., and Lake, B. M. (2022). Creativity, Compositionality, and Common Sense in Human Goal Generation. In Proceedings of the 44th Annual Conference of the Cognitive Science Society.

Ruis, L. and Lake, B. M. (2022). Improving Systematic Generalization Through Modularity and Augmentation. In Proceedings of the 44th Annual Conference of the Cognitive Science Society. [Code]


2021

Feinman, R. and Lake, B. M. (2021). Learning Task-General Representations with Generative Neuro-Symbolic Modeling. International Conference on Learning Representations (ICLR). [Code]

Gandhi, K., Stojnic, G., Lake, B. M. and Dillon, M. R. (2021). Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others. Advances in Neural Information Processing Systems (NeurIPS) 34 . [Supporting Info.][Dataset]

Nye, M., Tessler, M. H., Tenenbaum, J. B., and Lake, B. M. (2021). Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning. Advances in Neural Information Processing Systems (NeurIPS) 34 . [Supporting Info.]

Vedantam, R., Szlam, A., Nickel M., Morcos, A., and Lake, B. M. (2021). CURI: A Benchmark for Productive Concept Learning Under Uncertainty. International Conference on Machine Learning (ICML). [Supporting Info.][Data and Code]

Zhou, Y. and Lake, B. M. (2021). Flexible compositional learning of structured visual concepts. In Proceedings of the 43rd Annual Conference of the Cognitive Science Society.

Tartaglini, A. R., Vong, W. K., and Lake, B. M. (2021). Modeling artificial category learning from pixels: Revisiting Shepard, Hovland, and Jenkins (1961) with deep neural networks. In Proceedings of the 43rd Annual Conference of the Cognitive Science Society.

Davidson, G. and Lake, B. M. (2021). Examining Infant Relation Categorization Through Deep Neural Networks. In Proceedings of the 43rd Annual Conference of the Cognitive Science Society.

Johnson, A., Vong, W. K., Lake, B. M. and Gureckis, T. M. (2021). Fast and flexible: Human program induction in abstract reasoning tasks. In Proceedings of the 43rd Annual Conference of the Cognitive Science Society.

Wang, Z. and Lake, B. M. (2021). Modeling question asking using neural program generation. In Proceedings of the 43rd Annual Conference of the Cognitive Science Society. [Code]


2020

Lake, B. M. and Piantadosi, S. T. (2020). People infer recursive visual concepts from just a few examples. Computational Brain & Behavior, 3(1), 54-65. [Supporting Info.] [Experiments]

Lewis, M., Cristiano, V., Lake, B. M., Kwan, T., and Frank, M. C. (2020). The role of developmental change and linguistic experience in the mutual exclusivity effect. Cognition, 198.

Orhan, A. E., Gupta, V. B., and Lake, B. M. (2020). Self-supervised learning through the eyes of a child. Advances in Neural Information Processing Systems (NeurIPS) 33. [Supporting Info.] [Code and pre-trained models]

Ruis, L., Andreas, J., Baroni, M. Bouchacourt, D., and Lake, B. M. (2020). A Benchmark for Systematic Generalization in Grounded Language Understanding. Advances in Neural Information Processing Systems (NeurIPS) 33. [Supporting Info.] [Benchmark] [Baseline model]

Nye, M., Solar-Lezama, A., Tenenbaum, J. B., and Lake, B. M. (2020). Learning Compositional Rules via Neural Program Synthesis. Advances in Neural Information Processing Systems (NeurIPS) 33. [Supporting Info.] [Code]

Gandhi, K. and Lake, B. M. (2020). Mutual exclusivity as a challenge for deep neural networks. Advances in Neural Information Processing Systems (NeurIPS) 33. [Supporting Info.]

Feinman, R. and Lake, B. M. (2020). Generating new concepts with hybrid neuro-symbolic models. In Proceedings of the 42nd Annual Conference of the Cognitive Science Society. [Short video] [Supporting Info.]

Davidson, G. and Lake, B. M. (2020). Investigating simple object representations in model-free deep reinforcement learning. In Proceedings of the 42nd Annual Conference of the Cognitive Science Society. [Short video]


2019

Lake, B. M., Salakhutdinov, R., and Tenenbaum, J. B. (2019). The Omniglot challenge: a 3-year progress report. Current Opinion in Behavioral Sciences, 29, 97-104.

Lake, B. M. (2019). Compositional generalization through meta sequence-to-sequence learning. Advances in Neural Information Processing Systems (NeurIPS) 32. [Code]

Feinman, R. and Lake, B. M. (2019). Learning a smooth kernel regularizer for convolutional neural networks. In Proceedings of the 41st Annual Conference of the Cognitive Science Society.

Lake, B. M., Linzen, T., and Baroni, M. (2019). Human few-shot learning of compositional instructions. In Proceedings of the 41st Annual Conference of the Cognitive Science Society.

Rothe, A., Lake, B. M., and Gureckis, T. M. (2019). Asking goal-oriented questions and learning from answers. In Proceedings of the 41st Annual Conference of the Cognitive Science Society.


2018

Rothe, A., Lake, B. M., and Gureckis, T. M. (2018). Do people ask good questions? Computational Brain & Behavior, 1(1), 69-89.

Lake, B. M., Lawrence, N. D., and Tenenbaum, J. B. (2018). The emergence of organizing structure in conceptual representation. Cognitive Science, 42(S3), 809-832. [Supporting Info.] [Code]

Lake, B. M. and Baroni, M. (2018). Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks. International Conference on Machine Learning (ICML). [Supporting Info.] [Data set]

Feinman, R. and Lake, B. M. (2018). Learning inductive biases with simple neural networks. In Proceedings of the 40th Annual Conference of the Cognitive Science Society.

Loula, J., Baroni, M., and Lake, B. M. (2018). Rearranging the familiar: Testing compositional generalization in recurrent networks. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP.


2017

Lake, B. M., Ullman, T. D., Tenenbaum, J. B., and Gershman, S. J. (2017). Building machines that learn and think like people. Behavioral and Brain Sciences, 40, E253.

Rothe, A., Lake, B. M., and Gureckis, T. M. (2017). Question asking as program generation. Advances in Neural Information Processing Systems (NeurIPS) 30. [Supporting Info.]


2016

Rothe, A., Lake, B. M., and Gureckis, T. M. (2016). Asking and evaluating natural language questions. In Proceedings of the 38th Annual Conference of the Cognitive Science Society.

Cohen, A. and Lake, B. M. (2016). Searching large hypothesis spaces by asking questions. In Proceedings of the 38th Annual Conference of the Cognitive Science Society.


2015

Lake, B. M., Salakhutdinov, R., and Tenenbaum, J. B. (2015). Human-level concept learning through probabilistic program induction. Science, 350(6266), 1332-1338. [Supporting Info.] [visual Turing tests] [Omniglot data set] [Bayesian Program Learning code]

Monfort, M., Lake, B. M., Ziebart, B. D., Lucey, P., and Tenenbaum, J. B. (2015). Softstar: Heuristic-Guided Probabilistic Inference. Advances in Neural Information Processing Systems (NeurIPS) 28. [Supporting Info.]

Lake, B. M., Zaremba, W., Fergus, R. and Gureckis, T. M. (2015). Deep Neural Networks Predict Category Typicality Ratings for Images. In Proceedings of the 37th Annual Conference of the Cognitive Science Society. [Data]


2014 and earlier

Lake, B. M. (2014). Towards more human-like concept learning in machines: Compositionality, causality, and learning-to-learn. Ph.D. thesis, MIT.

Lake, B. M., Lee, C.-y., Glass, J. R., and Tenenbaum, J. B. (2014). One-shot learning of generative speech concepts. In Proceedings of the 36th Annual Conference of the Cognitive Science Society. [Supporting Info.]

Lake, B. M., Salakhutdinov, R., and Tenenbaum, J. B. (2013). One-Shot Learning by Inverting a Compositional Causal Process. Advances in Neural Information Processing Systems (NeurIPS) 26. [Supporting Info.]

Lake, B. M., Salakhutdinov, R., and Tenenbaum, J. B. (2012). Concept learning as motor program induction: A large-scale empirical study. In Proceedings of the 34th Annual Conference of the Cognitive Science Society. [Supporting Info.]

Lake, B. M., Salakhutdinov, R., Gross, J., and Tenenbaum, J. B. (2011). One shot learning of simple visual concepts. In Proceedings of the 33rd Annual Conference of the Cognitive Science Society. [Videos]

Lake, B. M. and McClelland, J. L. (2011). Estimating the strength of unlabeled information during semi-supervised learning. In Proceedings of the 33rd Annual Conference of the Cognitive Science Society.

Lake, B. M. and Tenenbaum, J. B. (2010). Discovering Structure by Learning Sparse Graphs. In Proceedings of the 32nd Annual Conference of the Cognitive Science Society.

Lake, B. M. (2009). Unsupervised and semi-supervised perceptual category learning. Master’s thesis, Stanford University.

Lake, B. M., Vallabha, G. K., and McClelland, J. L. (2009). Modeling unsupervised perceptual category learning. IEEE Transactions on Autonomous Mental Development, 1(1), 35-43.

Lake, B. M., Vallabha, G. K., and McClelland, J. L. (2008). Modeling unsupervised perceptual category learning. In Proceedings of the 7th International Conference on Development and Learning.

Lake, B. M. and Cottrell, G.W. (2005). Age of acquisition in facial identification: A connectionist approach. In Proceedings of the 27th Annual Conference of the Cognitive Science Society.