Ari Morcos

About Me


I am a research scientist at Facebook AI Research (FAIR) in Menlo Park, working on using neuroscience-inspired approaches to understand and build better machine learning systems. Previously, I worked at DeepMind in London.

I earned my PhD working with Chris Harvey at Harvard University . For my thesis, I developed methods to understand how neuronal circuits perform the computations necessary for complex behavior. In particular, my research focused on how parietal cortex contributes to evidence accumulation decision-making.

For my undergraduate work, I attended UCSD, where I worked with Fred Gage to investigate the role of REST/NRSF in adult neurogenesis.

When I'm not working, I like to go on adventures with my wife, Julia, and our awesome dog, Dash. I'm also a history buff and love learning about the history of science, the two World Wars, and the Cold War.

Recent news

See all news

Selected publications

Insights on representational similarity in neural networks with canonical correlation

Ari S Morcos*, Maithra Raghu*, and Samy Bengio
Neural Information Processing Systems (NeurIPS), 2018.

Neural scene representation and rendering

SM Ali Eslami*, Danilo J Rezende*, Frederic Besse, Fabio Viola, Ari S Morcos, Marta Garnelo, Avraham Ruderman, Andrei A. Rusu, Ivo Danihelka, Karol Gregor, David P. Reichert, Lars Beusing, Theophane Weber, Oriol Vinyals, Dan Rosenbaum, Neil C Rabinowitz, Helen King, Chloe Hillier, Matthew Botvinick, Daan Wierstra, Koray Kavukcuoglu, and Demis Hassabis
Science 15 Jun 2018, Vol. 360, Issue 6394, pp. 1204-1210, doi: 10.1126/science.aar6170

On the importance of single directions for generalization

Ari S Morcos, David GT Barrett, Neil C Rabinowitz, and Matthew Botvinick
International Conference on Learning Representations (ICLR), 2018

History-dependent variability in population dynamics during evidence accumulation in cortex

Ari S Morcos and Christopher D Harvey
Nature Neuroscience vol. 19, no. 12, pp. 1672–1681, 2016. doi: 10.1038/nn.4403.

See all publications