Andrew M. Saxe

Publication Activity (10 Years)

Years Active: 2006-2024
Publications (10 Years): 38

Top Topics

Long Term Memory

Matrix Factorization

Top Venues

Publications

Loek van Rossem, Andrew M. Saxe
When Representations Align: Universality in Representation Learning Dynamics. CoRR (2024)
Jirko Rubruck, Jan P. Bauer, Andrew M. Saxe, Christopher Summerfield
Early learning of the optimal constant solution in neural networks and humans. CoRR (2024)
Aaditya K. Singh, Ted Moskovitz, Felix Hill, Stephanie C. Y. Chan, Andrew M. Saxe
What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation. CoRR (2024)
Stefano Sarao Mannelli, Yaraslau Ivashinka, Andrew M. Saxe, Luca Saglietti
Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks. CoRR (2024)
Daniel Kunin, Allan Raventós, Clémentine Dominé, Feng Chen, David Klindt, Andrew M. Saxe, Surya Ganguli
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning. CoRR (2024)
Aaditya K. Singh, Stephanie C. Y. Chan, Ted Moskovitz, Erin Grant, Andrew M. Saxe, Felix Hill
The Transient Nature of Emergent In-Context Learning in Transformers. NeurIPS (2023)
Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M. Saxe
On The Specialization of Neural Modules. ICLR (2023)
Aaditya K. Singh, Stephanie C. Y. Chan, Ted Moskovitz, Erin Grant, Andrew M. Saxe, Felix Hill
The Transient Nature of Emergent In-Context Learning in Transformers. CoRR (2023)
Anika T. Löwe, Léo Touzo, Paul S. Muhle-Karbe, Andrew M. Saxe, Christopher Summerfield, Nicolas W. Schuck
Regularised neural networks mimic human insight. CoRR (2023)
Timo Flesch, David G. Nagy, Andrew M. Saxe, Christopher Summerfield
Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals. PLoS Comput. Biol. 19 (1) (2023)
Rodrigo Carrasco-Davis, Javier Masís, Andrew M. Saxe
Meta-Learning Strategies through Value Maximization in Neural Networks. CoRR (2023)
Andrew M. Saxe, Shagun Sodhani, Sam Jay Lewallen
The Neural Race Reduction: Dynamics of Abstraction in Gated Networks. CoRR (2022)
Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe
An Analytical Theory of Curriculum Learning in Teacher-Student Networks. NeurIPS (2022)
Federica Gerace, Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe, Lenka Zdeborová
Probing transfer learning with a model of synthetic correlated datasets. Mach. Learn. Sci. Technol. 3 (1) (2022)
Sebastian Lee, Stefano Sarao Mannelli, Claudia Clopath, Sebastian Goldt, Andrew M. Saxe
Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation. CoRR (2022)
Andrew M. Saxe, Shagun Sodhani, Sam Jay Lewallen
The Neural Race Reduction: Dynamics of Abstraction in Gated Networks. ICML (2022)
Sebastian Lee, Stefano Sarao Mannelli, Claudia Clopath, Sebastian Goldt, Andrew M. Saxe
Maslow's Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation. ICML (2022)
Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe
An Analytical Theory of Curriculum Learning in Teacher-Student Networks. CoRR (2021)
Federica Gerace, Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe, Lenka Zdeborová
Probing transfer learning with a model of synthetic correlated datasets. CoRR (2021)
Sebastian Lee, Sebastian Goldt, Andrew M. Saxe
Continual Learning in the Teacher-Student Setup: Impact of Task Similarity. CoRR (2021)
Sebastian Lee, Sebastian Goldt, Andrew M. Saxe
Continual Learning in the Teacher-Student Setup: Impact of Task Similarity. ICML (2021)
Madhu S. Advani, Andrew M. Saxe, Haim Sompolinsky
High-dimensional dynamics of generalization error in neural networks. Neural Networks 132 (2020)
Sebastian Goldt, Madhu Advani, Andrew M. Saxe, Florent Krzakala, Lenka Zdeborová
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup. NeurIPS (2019)
Sebastian Goldt, Madhu S. Advani, Andrew M. Saxe, Florent Krzakala, Lenka Zdeborová
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup. CoRR (2019)
Sebastian Goldt, Madhu S. Advani, Andrew M. Saxe, Florent Krzakala, Lenka Zdeborová
Generalisation dynamics of online learning in over-parameterised neural networks. CoRR (2019)
Andrew M. Saxe, Yamini Bansal, Joel Dapello, Madhu Advani, Artemy Kolchinsky, Brendan D. Tracey, David D. Cox
On the Information Bottleneck Theory of Deep Learning. ICLR (Poster) (2018)
Andrew M. Saxe, James L. McClelland, Surya Ganguli
A mathematical theory of semantic development in deep neural networks. CoRR (2018)
Yamini Bansal, Madhu Advani, David D. Cox, Andrew M. Saxe
Minnorm training: an algorithm for training over-parameterized deep neural networks. CoRR (2018)
Adam Christopher Earle, Andrew M. Saxe, Benjamin Rosman
Hierarchical Subtask Discovery with Non-Negative Matrix Factorization. ICLR (Poster) (2018)
Yao Zhang, Andrew M. Saxe, Madhu S. Advani, Alpha A. Lee
Energy-entropy competition and the effectiveness of stochastic gradient descent in machine learning. CoRR (2018)
Madhu S. Advani, Andrew M. Saxe
High-dimensional dynamics of generalization error in neural networks. CoRR (2017)
Andrew M. Saxe, Adam Christopher Earle, Benjamin Rosman
Hierarchy Through Composition with Multitask LMDPs. ICML (2017)
Adam Christopher Earle, Andrew M. Saxe, Benjamin Rosman
Hierarchical Subtask Discovery With Non-Negative Matrix Factorization. CoRR (2017)
James L. McClelland, Steven Stenberg Hansen, Andrew M. Saxe
Tutorial Workshop on Contemporary Deep Neural Network Models. CogSci (2016)
Chuan-Yung Tsai, Andrew M. Saxe, David D. Cox
Tensor Switching Networks. NIPS (2016)
Tommaso Furlanello, Jiaping Zhao, Andrew M. Saxe, Laurent Itti, Bosco S. Tjan
Active Long Term Memory Networks. CoRR (2016)
Chuan-Yung Tsai, Andrew M. Saxe, David D. Cox
Tensor Switching Networks. CoRR (2016)
Andrew M. Saxe, Adam Christopher Earle, Benjamin Rosman
Hierarchy through Composition with Linearly Solvable Markov Decision Processes. CoRR (2016)
Andrew M. Saxe
Deep Learning and the Brain. CogSci (2014)
Rachel Lee, Andrew M. Saxe
Modeling Perceptual Learning with Deep Networks. CogSci (2014)
Andrew M. Saxe, James L. McClelland, Surya Ganguli
Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. ICLR (2014)
Andrew M. Saxe
Multitask model-free reinforcement learning. CogSci (2014)
Andrew M. Saxe, James L. McClelland, Surya Ganguli
Learning hierarchical categories in deep neural networks. CogSci (2013)
Andrew M. Saxe, Pang Wei Koh, Zhenghao Chen, Maneesh Bhand, Bipin Suresh, Andrew Y. Ng
On Random Weights and Unsupervised Feature Learning. ICML (2011)
Andrew M. Saxe, Maneesh Bhand, Ritvik Mudur, Bipin Suresh, Andrew Y. Ng
Unsupervised learning models of primary cortical receptive fields and receptive field plasticity. NIPS (2011)
Ian J. Goodfellow, Quoc V. Le, Andrew M. Saxe, Honglak Lee, Andrew Y. Ng
Measuring Invariances in Deep Networks. NIPS (2009)
Anand R. Atreya, Bryan C. Cattle, Brendan M. Collins, Benjamin Essenburg, Gordon H. Franken, Andrew M. Saxe, Scott N. Schiffres, Alain L. Kornhauser
Prospect Eleven: Princeton University's entry in the 2005 DARPA Grand Challenge. J. Field Robotics 23 (9) (2006)