Andrew Saxe

Publication Activity (10 Years)

Years Active: 2016-2024
Publications (10 Years): 13

Top Topics

Causal Relations

Top Venues

Publications

Yedi Zhang, Andrew Saxe, Peter E. Latham
When Are Bias-Free ReLU Networks Like Linear Networks? CoRR (2024)
Yedi Zhang, Peter E. Latham, Andrew Saxe
A Theory of Unimodal Bias in Multimodal Learning. CoRR (2023)
Aaditya K. Singh, David Ding, Andrew Saxe, Felix Hill, Andrew K. Lampinen
Know your audience: specializing grounded language models with listener subtraction. EACL (2023)
Timo Flesch, Andrew Saxe, Christopher Summerfield
Continual task learning in natural and artificial agents. CoRR (2022)
Timo Flesch, David G. Nagy, Andrew Saxe, Christopher Summerfield
Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals. CoRR (2022)
Lukas Braun, Clémentine Dominé, James Fitzgerald, Andrew Saxe
Exact learning dynamics of deep linear networks with prior knowledge. NeurIPS (2022)
Aaditya K. Singh, David Ding, Andrew Saxe, Felix Hill, Andrew K. Lampinen
Know your audience: specializing grounded language models with the game of Dixit. CoRR (2022)
Keno Juechems, Andrew Saxe
Inferring Actions, Intentions, and Causal Relations in a Deep Neural Network. CogSci (2021)
Yinan Cao, Christopher Summerfield, Andrew Saxe
Characterizing emergent representations in a space of candidate learning rules for deep networks. NeurIPS (2020)
Maxwell Nye, Andrew Saxe
Are Efficient Deep Representations Learnable? CoRR (2018)
Maxwell Nye, Andrew Saxe
Are Efficient Deep Representations Learnable? ICLR (Workshop) (2018)
Sebastian Musslick, Andrew Saxe, Kayhan Özcimder, Biswadip Dey, Greg Henselman, Jonathan D. Cohen
Multitasking Capability Versus Learning Efficiency in Neural Network Architectures. CogSci (2017)
Andrew Saxe
Inferring actions, intentions, and causal relations in a neural network. CogSci (2016)