I am a PhD Candidate in the Caltech Computer Vision Lab, advised by Pietro Perona. I also collaborate with Meister Lab. My research focuses on sequential decision making in brains and machines. This involves topics spanning AI and naturalistic behavior, including computer vision, machine learning / reinforcement learning, systems neuroscience, and behavior modeling and prediction.

Currently, I work on 1) understanding long-horizon decision making using graph-based mazes, 2) explainable ML models of complex behavior, and 3) deep learning for modeling biological organisms from multiple modalities. I believe we build better AI by learning about intelligence from its source. On the applied side, I am interested in problems that deal with spatiotemporal data and decision-making.

Previous to Caltech in my undergrad, I worked with various organizations internationally in advancing public policy, including the WHO, and theoretical neuroscience, as a Loran Scholar.

Get in touch.


9/2021: I’ll be in Ann Arbor from 9/30 - 10/2 for an invited talk about our recent maze work at the Annual Meeting of the Pavlovian Society.

8/2021: Caltech featured our research on the homepage! Read the story or watch the interview to learn more about the inspirations behind the work.

7/2021: Our paper on fast sequential learning has been published in eLife.

1/2021: Our first full report characterizing and modeling few-shot learning and efficient exploration in a complex hierarchical maze is out on arxiv.

9/2020: I’ve returned to Caltech full-time while remaining the ML Lead for a confidential Google X project part-time.

6/2020: I joined Google X as a AI Resident, continuing work on ML for behavior with multiple modalities.

10/2019: Our work on rapid learning and intrinsic motivated exploration in complex maze environments for mice has been accepted to the NeurIPS Biological and Artificial Reinforcement Learning workshop

3/2019: I presented our work on automated training and iterative latent strategy inference at the SoCal Machine Learning Symposium


Long-Term Tracking and Classification of Invidual Behavior in Bumble Bee Colonies
Matthew Smith, August Easton-Calabria, Tony Zhang, et al.
Journal of Artificial Life and Robotics

Mice in a labyrinth: Rapid learning, sudden insight, and efficient exploration
Matthew Rosenberg*, Tony Zhang*, Pietro Perona, Markus Meister
[eLife] [Arxiv]

Semi-Supervised Audio Representation Learning for Modeling Beehive Strengths
Tony Zhang, Szymon Zmyslony, Sergei Nozdrenkov, Matthew Smith, Brandon Hopkins

Rapid learning and efficient exploration by mice navigating a complex maze
Matthew Rosenberg*, Tony Zhang*, Pietro Perona, Markus Meister
[NeurIPS 2019 Bio & Artificial RL]

Mouse Academy: high-throughput automated training and trial-by-trial behavioral analysis during learning
Mu Qiao, Tony Zhang, Cristina Segalin, Sarah Sam, Pietro Perona, Markus Meister
[SoCal ML Symposium ‘19] [Arxiv]