I am a research scientist at Facebook AI Research working on understanding the mechanisms underlying neural network computation and function, and using these insights to build machine learning systems more intelligently. In particular, I’ve worked on understanding the properties predictive of generalization, methods to compare representations across networks, the role of single units in computation, and on strategies to measure abstraction in neural network representations. Previously, I worked at DeepMind in London, and I earned my PhD in neurobiology at Harvard University, using machine learning to study the cortical dynamics underlying evidence accumulation for decision-making.
Interests
Understanding deep learning, generalization, abstract reasoning, computer vision, representation learning
Latest Publications
Learning for Dynamics & Control (L4DC) - June 10, 2020
Plan2vec: Unsupervised Representation Learning by Latent Plans
Ge Yang, Amy Zhang, Ari Morcos, Joelle Pineau, Pieter Abbeel, Roberto Calandra
ICLR - April 27, 2020
The Early Phase of Neural Network Training
Jonathan Frankle, David J. Schwab, Ari Morcos
ICLR - April 26, 2020
DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
Erik Wijmans, Abhishek Kadian, Ari Morcos, Stefan Lee, Irfan Essa, Devi Parikh, Manolis Savva, Dhruv Batra
NeurIPS - December 10, 2019
One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers
Ari Morcos, Haonan Yu, Michela Paganini, Yuandong Tian
ICLR - May 10, 2019
Insights on Visual Representations for Embodied Navigation Tasks
Erik Wijmans, Julian Straub, Dhruv Batra, Judy Hoffman, Ari Morcos