Ari S. Morcos
Ari S. Morcos
Research Scientist, Meta AI Research
Verified email at - Homepage
Cited by
Cited by
Human-level performance in 3D multiplayer games with population-based reinforcement learning
M Jaderberg, WM Czarnecki, I Dunning, L Marris, G Lever, AG Castaneda, ...
Science 364 (6443), 859-865, 2019
Neural scene representation and rendering
SMA Eslami, D Jimenez Rezende, F Besse, F Viola, AS Morcos, ...
Science 360 (6394), 1204-1210, 2018
Convit: Improving vision transformers with soft convolutional inductive biases
S d'Ascoli, H Touvron, M Leavitt, A Morcos, G Biroli, L Sagun
International Conference on Machine Learning (ICML) 2021, 2021
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
M Wortsman, G Ilharco, SY Gadre, R Roelofs, R Gontijo-Lopes, ...
International Conference on Machine Learning, 23965-23998, 2022
Insights on representational similarity in neural networks with canonical correlation
AS Morcos, M Raghu, S Bengio
Neural Information Processing Systems (NeurIPS), 2018
Decentralized Distributed PPO: Solving PointGoal Navigation
E Wijmans, A Kadian, A Morcos, S Lee, I Essa, D Parikh, M Savva, ...
International Conference on Learning Representations (ICLR), 2020
On the importance of single directions for generalization
AS Morcos, DGT Barrett, NC Rabinowitz, M Botvinick
International Conference on Learning Representations (ICLR), 2018
Measuring abstract reasoning in neural networks
A Santoro, F Hill, D Barrett, A Morcos, T Lillicrap
International conference on machine learning, 4477-4486, 2018
History-dependent variability in population dynamics during evidence accumulation in cortex
AS Morcos, CD Harvey
Nature neuroscience 19 (12), 1672-1681, 2016
One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers
AS Morcos, H Yu, M Paganini, Y Tian
Neural Information Processing Systems (NeurIPS), 2019
The early phase of neural network training
J Frankle, DJ Schwab, AS Morcos
International Conference on Learning Representations (ICLR), 2020
Beyond neural scaling laws: beating power law scaling via data pruning
B Sorscher, R Geirhos, S Shekhar, S Ganguli, AS Morcos
Neural Information Processing Systems (NeurIPS) [Outstanding Paper], 2022
Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP
H Yu, S Edunov, Y Tian, AS Morcos
International Conference on Learning Representations (ICLR), 2020
Training batchnorm and only batchnorm: On the expressive power of random features in cnns
J Frankle, DJ Schwab, AS Morcos
International Conference on Learning Representations (ICLR), 2021
Analyzing biological and artificial neural networks: challenges with opportunities for synergy?
DGT Barrett, AS Morcos, JH Macke
Current opinion in neurobiology 55, 55-64, 2019
A cookbook of self-supervised learning
R Balestriero, M Ibrahim, V Sobal, A Morcos, S Shekhar, T Goldstein, ...
arXiv preprint arXiv:2304.12210, 2023
Learning to Make Analogies by Contrasting Abstract Relational Structure
F Hill, A Santoro, D Barrett, A Morcos, T Lillicrap
International Conference on Learning Representations (ICLR), 2019
The generalization-stability tradeoff in neural network pruning
BR Bartoldson, AS Morcos, A Barbu, G Erlebacher
Neural Information Processing Systems (NeurIPS), 2020
Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs
A Ruderman, N Rabinowitz, AS Morcos, D Zoran
arXiv preprint arXiv:1804.04438, 2018
Towards falsifiable interpretability research
ML Leavitt, A Morcos
arXiv preprint arXiv:2010.12016, 2020
The system can't perform the operation now. Try again later.
Articles 1–20