Sotabase

Career

· Professor of Theoretical Neuroscience and Machine Learning, University College London2021–
· PhD in Electrical Engineering, Stanford University2009–2015
· BSE in Electrical Engineering, Princeton University2004–2008
· Swartz Postdoctoral Fellow, Harvard University
· MS in Electrical Engineering, Stanford University
· Associate Professor, University of Oxford

Publications (63)

Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
International Conference on Learning Representations · 2013
1,992
cited
A deep learning framework for neuroscience
Nature Neuroscience · 2019
928
cited
On the information bottleneck theory of deep learning
International Conference on Learning Representations · 2018
644
cited
High-dimensional dynamics of generalization error in neural networks
Neural Networks · 2017
509
cited
Measuring Invariances in Deep Networks
Neural Information Processing Systems · 2009
477
cited
On Random Weights and Unsupervised Feature Learning
International Conference on Machine Learning · 2011
452
cited
A mathematical theory of semantic development in deep neural networks
Proceedings of the National Academy of Sciences of the United States of America · 2018
308
cited
If deep learning is the answer, what is the question?
Nature Reviews Neuroscience · 2020
301
cited
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher–student setup
Neural Information Processing Systems · 2019
168
cited
Acquisition of decision making criteria: reward rate ultimately beats accuracy
Attention, perception & psychophysics · 2011
157
cited
Orthogonal representations for robust context-dependent task performance in brains and neural networks
Neuron · 2022
123
cited
Continual Learning in the Teacher-Student Setup: Impact of Task Similarity
International Conference on Machine Learning · 2021
91
cited
Organizing memories for generalization in complementary learning systems
bioRxiv · 2021
69
cited
Energy–entropy competition and the effectiveness of stochastic gradient descent in machine learning
Molecular Physics · 2018
61
cited
Exact learning dynamics of deep linear networks with prior knowledge
Journal of statistical mechanics · 2023
58
cited
Unsupervised learning models of primary cortical receptive fields and receptive field plasticity
Neural Information Processing Systems · 2011
55
cited
Learning hierarchical category structure in deep neural networks
2013
47
cited
Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals
PLoS Comput. Biol. · 2022
45
cited
The Neural Race Reduction: Dynamics of Abstraction in Gated Networks
International Conference on Machine Learning · 2022
45
cited
Multitasking Capability Versus Learning Efficiency in Neural Network Architectures
Annual Meeting of the Cognitive Science Society · 2017
44
cited
Sotabase
Andrew Saxe | Researcher Profile | Sotabase | Sotabase