Andrew M. Saxe

发表

Measuring Invariances in Deep Networks

Quoc V. Le, Honglak Lee, Andrew Y. Ng, 2009, NIPS.

Unsupervised learning models of primary cortical receptive fields and receptive field plasticity

Andrew Y. Ng, Bipin Suresh, Andrew M. Saxe, 2011, NIPS.

Hierarchy through Composition with Linearly Solvable Markov Decision Processes pdf

Benjamin Rosman, Andrew M. Saxe, Adam Christopher Earle, 2016, ArXiv.

Hierarchy Through Composition with Multitask LMDPs

Benjamin Rosman, Andrew M. Saxe, Adam Christopher Earle, 2017, ICML.

Minnorm training: an algorithm for training over-parameterized deep neural networks pdf

David D. Cox, Andrew M. Saxe, Yamini Bansal, 2018, ArXiv.

Deep Learning and the Brain

Andrew M. Saxe, 2014, CogSci.

Generalisation dynamics of online learning in over-parameterised neural networks pdf

Florent Krzakala, Lenka Zdeborová, Andrew M. Saxe, 2019, ArXiv.

Tensor Switching Networks

David D. Cox, Andrew M. Saxe, Chuan-Yung Tsai, 2016, NIPS.

Rats strategically manage learning during perceptual decision making

David D. Cox, Andrew M. Saxe, Javier Masís, 2020, bioRxiv.

A mathematical theory of semantic development in deep neural networks

Surya Ganguli, James L. McClelland, Andrew M. Saxe, 2018, Proceedings of the National Academy of Sciences.

Hierarchical Subtask Discovery With Non-Negative Matrix Factorization pdf

Benjamin Rosman, Andrew M. Saxe, Adam Christopher Earle, 2017, ICLR.

Tutorial Workshop on Contemporary Deep Neural Network Models

James L. McClelland, Andrew M. Saxe, Steven Stenberg Hansen, 2016, CogSci.

Incremental Hierarchical Reinforcement Learning with Multitask LMDPs

Benjamin Rosman, Andrew M. Saxe, Adam Christopher Earle, 2018 .

A Critique of Pure Hierarchy: Uncovering Cross-Cutting Structure in a Natural Dataset

James L. McClelland, Zahra Sadeghi, Andrew M. Saxe, 2016 .

Prospect Eleven: Princeton University's entry in the 2005 DARPA Grand Challenge: Field Reports

Alain L. Kornhauser, Andrew M. Saxe, Gordon H. Franken, 2006 .

On Random Weights and Unsupervised Feature Learning

Zhenghao Chen, Andrew Y. Ng, Bipin Suresh, 2011, ICML.

Active Long Term Memory Networks pdf

Laurent Itti, Jiaping Zhao, Bosco S. Tjan, 2016, ArXiv.

DARPA Urban Challenge Princeton University Technical Paper

Alain L. Kornhauser, Jonathan Mayer, Andrew M. Saxe, 2007 .

Prospect Eleven: Princeton University's entry in the 2005 DARPA Grand Challenge

Alain L. Kornhauser, Andrew M. Saxe, Gordon H. Franken, 2006, J. Field Robotics.

Modeling Perceptual Learning with Deep Networks

Rachel Lee, Andrew M. Saxe, 2014, CogSci.

Exact solutions to the nonlinear dynamics of learning in deep linear neural networks pdf

Surya Ganguli, James L. McClelland, Andrew M. Saxe, 2013, ICLR.

On the information bottleneck theory of deep learning

David D. Cox, Artemy Kolchinsky, Andrew M. Saxe, 2018, ICLR.

Dynamics of stochastic gradient descent for two-layer neural networks in the teacher–student setup pdf

Florent Krzakala, Lenka Zdeborová, Andrew M. Saxe, 2019, NeurIPS.

Learning hierarchical categories in deep neural networks

Surya Ganguli, James L. McClelland, Andrew M. Saxe, 2013, CogSci.

Energy–entropy competition and the effectiveness of stochastic gradient descent in machine learning

Yao Zhang, Alpha A. Lee, Andrew M. Saxe, 2018, Molecular Physics.

Multitask model-free reinforcement learning

Andrew M. Saxe, 2014, CogSci.

High-dimensional dynamics of generalization error in neural networks

Andrew M. Saxe, Madhu S. Advani, Madhu S. Advani, 2017, Neural Networks.

Learning Dynamics of Deep Networks Admit Low-Rank Tensor Descriptions

Surya Ganguli, Andrew M. Saxe, Alex H. Williams, 2018 .

Learning hierarchical category structure in deep neural networks

James L. McClelland, Andrew M. Saxe, S. Ganguli, 2013 .

Acquisition of decision making criteria: reward rate ultimately beats accuracy

Andrew M. Saxe, Jonathan D. Cohen, P. Holmes, 2011, Attention, perception & psychophysics.

On the Rational Boundedness of Cognitive Control: Shared Versus Separated Representations

Andrew M. Saxe, Jonathan D. Cohen, Sebastian Musslick, 2020 .

Neural knowledge assembly in humans and deep networks

Andrew M. Saxe, C. Summerfield, Stephanie Nelli, 2021 .

Supplementary Information : A mathematical theory of semantic development in deep neural networks

James L. McClelland, Andrew M. Saxe, S. Ganguli, 2019 .

Minnorm training: an algorithm for training overcomplete deep neural networks

Andrew M. Saxe, Yamini Bansal, Madhu Advani, 2018 .

Learning hierarchical category structure in deep neural networks

James L. McClelland, Andrew M. Saxe, S. Ganguli, 2013 .

Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation

Andrew M. Saxe, Stefano Sarao Mannelli, C. Clopath, 2022, ICML.

Know your audience: specializing grounded language models with the game of Dixit

Andrew Kyle Lampinen, Andrew M. Saxe, Felix Hill, 2022, ArXiv.

The Neural Race Reduction: Dynamics of Abstraction in Gated Networks

Andrew M. Saxe, Sam Lewallen, Shagun Sodhani, 2022, ICML.

Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation

Andrew M. Saxe, Stefano Sarao Mannelli, C. Clopath, 2022, ArXiv.

Know your audience: specializing grounded language models with the game of Dixit

Andrew Kyle Lampinen, Andrew M. Saxe, Felix Hill, 2022, ArXiv.

An analytical theory of curriculum learning in teacher–student networks

Andrew M. Saxe, Stefano Sarao Mannelli, Luca Saglietti, 2021, NeurIPS.

Continual task learning in natural and artificial agents

Andrew M. Saxe, C. Summerfield, Timo Flesch, 2022, Trends in Neurosciences.

An analytical theory of curriculum learning in teacher–student networks pdf

Luca Saglietti, Andrew M. Saxe, Andrew Saxe, 2021, Journal of Statistical Mechanics: Theory and Experiment.

Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals

Andrew M. Saxe, C. Summerfield, Timo Flesch, 2022, PLoS Comput. Biol..

Characterizing emergent representations in a space of candidate learning rules for deep networks

Christopher Summerfield, Andrew M. Saxe, Andrew Saxe, 2020, NeurIPS.

If deep learning is the answer, what is the question?

Andrew M. Saxe, Christopher Summerfield, Andrew Saxe, 2020, Nature Reviews Neuroscience.

Organizing memories for generalization in complementary learning systems

Andrew M. Saxe, James E. Fitzgerald, N. Spruston, 2021, bioRxiv.

A deep learning framework for neuroscience

Surya Ganguli, Yoshua Bengio, Claudia Clopath, 2019, Nature Neuroscience.

If deep learning is the answer, what is the question?

Andrew M. Saxe, C. Summerfield, Stephanie Nelli, 2020, Nature Reviews Neuroscience.

If deep learning is the answer, then what is the question?

Andrew M. Saxe, Christopher Summerfield, Andrew Saxe, 2020, 2004.07580.

Multitasking Capability Versus Learning Efficiency in Neural Network Architectures

Jonathan D. Cohen, Sebastian Musslick, Kayhan Özcimder, 2017, CogSci.

Neural knowledge assembly in humans and neural networks

Andrew M. Saxe, C. Summerfield, Stephanie Nelli, 2023, Neuron.

Strategically managing learning during perceptual decision making

Andrew M. Saxe, Juliana Y. Rhee, T. Chapman, 2023, eLife.

Orthogonal representations for robust context-dependent task performance in brains and neural networks

Andrew M. Saxe, C. Summerfield, Keno Juechems, 2022, Neuron.

Know your audience: specializing grounded language models with listener subtraction

Andrew Kyle Lampinen, Andrew M. Saxe, Felix Hill, 2022, EACL.

Rich and lazy learning of task representations in brains and neural networks

Andrew M. Saxe, C. Summerfield, Keno Juechems, 2021, bioRxiv.

Title: Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals Short title: A neural network model of human continual learning

Andrew M. Saxe, C. Summerfield, Timo Flesch, 2022 .

Continual Learning in the Teacher-Student Setup: Impact of Task Similarity

Andrew M. Saxe, Andrew Saxe, Sebastian Lee, 2021, ICML.

Neural knowledge assembly in humans and neural networks

Andrew M. Saxe, C. Summerfield, Stephanie Nelli, 2023, Neuron.

Regularised neural networks mimic human insight

Paul S. Muhle-Karbe, Andrew M. Saxe, Nicolas W. Schuck, 2023, 2023 Conference on Cognitive Computational Neuroscience.

Exact learning dynamics of deep linear networks with prior knowledge

Andrew M. Saxe, Lukas Braun, Clémentine Dominé, 2022, NeurIPS.

Probing transfer learning with a model of synthetic correlated datasets

Andrew M. Saxe, Luca Saglietti, Lenka Zdeborov'a, 2021, Mach. Learn. Sci. Technol..

Are task representations gated in macaque prefrontal cortex?

Andrew M. Saxe, W. Newsome, Valerio Mante, 2023, 2306.16733.

On The Specialization of Neural Modules

Andrew M. Saxe, Benjamin Rosman, Richard Klein, 2023, ICLR.

Kratos: Princeton University's entry in the 2008 Intelligent Ground Vehicle Competition

Andrew M. Saxe, Brenton A. Partridge, Solomon O. Abiola, 2009, Electronic Imaging.

Orthogonal representations for robust context-dependent task performance in brains and neural networks

Andrew M. Saxe, C. Summerfield, Keno Juechems, 2022, Neuron.

Exact learning dynamics of deep linear networks with prior knowledge

Andrew M. Saxe, Lukas Braun, James Fitzgerald, 2023, Journal of statistical mechanics.

Abrupt and spontaneous strategy switches emerge in simple regularised neural networks

Paul S. Muhle-Karbe, Andrew M. Saxe, Nicolas W. Schuck, 2023, 2302.11351.