Michael Chang

I am a Ph.D. student in Computer Science at U.C. Berkeley. I am a member of Berkeley AI Research.

This summer I was a research intern at Istituto Dalle Molle di Studi sull'Intelligenza Artificiale (IDSIA) under the supervision of Professor Jürgen Schmidhuber.

Earlier this year, I graduated with a B.S. in Computer Science from MIT, where I researched in CSAIL and BCS with Professors Josh Tenenbaum and Antonio Torralba.

Previously I worked at Google, at the University of Michigan Ann Arbor with Professor Honglak Lee, at the MIT Media Lab with Professor Pattie Maes, and as Strategy Lead in the MIT Solar Electric Vehicle Team.

Google Scholar  /  LinkedIn  /  Github  /  Twitter  /  Goodreads  /  Swimming

[ News | Talks | Research | Readings]

  • February 2017: "A Compositional Object-Based Approach to Learning Physical Dynamics" has been accepted to ICLR 2017.
  • March 2016: "Understanding Visual Concepts with Continuation Learning" has been accepted to ICLR 2016 Workshop.
  • March 2015: Press Article - Finger-Mounted Reading Device for the Blind, with Roy Shilkrot and Marcelo Polanco.

I am interested in recursive self-improvement, learning compositional programs, separating style and content, curiosity, and theory of mind.

Relational Neural Expectation Maximization
Sjoerd van Steenkiste, Michael Chang, Klaus Greff, Jürgen Schmidhuber
NIPS workshop on Cognitively Informed Artificial Intelligence, 2017
Oral Presentation

We propose a novel approach to common-sense physical reasoning that learns physical interactions between objects from raw visual images in a purely unsupervised fashion. Our method incorporates prior knowledge about the compositional nature of human perception, enabling it to discover objects, factor interactions between object-pairs to learn efficiently, and generalize to new environments without re-training.

A Compositional Object-Based Approach to Learning Physical Dynamics
Michael B. Chang, Tomer D. Ullman, Antonio Torralba, Joshua B. Tenenbaum
Proceedings of the International Conference on Learning Representations (ICLR), 2017
project webpage / code / poster / spotlight talk (NIPS Intuitive Physics Workshop)

The Neural Physics Engine (NPE) frames learning a simulator of intuitive physics as learning a compositional program over objects and interactions. This allows the NPE to naturally generalize across variable object count and different scene configurations.

Understanding Visual Concepts with Continuation Learning
William F. Whitney, Michael B. Chang, Tejas D. Kulkarni, Joshua B. Tenenbaum
International Conference on Learning Representations (ICLR) workshop, 2016
project webpage / code

This paper presents an unsupervised approach to learning factorized symbolic representations of high-level visual concepts by exploiting temporal continuity in the scene.


Here are some of my past and current readings that have changed the way I think.

Longer Works

The Society of Mind - Marvin Minsky

Three Kingdoms - Luo Guanzhong

The Beginning of Infinity - David Deutsch

The Little Prince - Antoine de Saint-Exupéry

Zhuangzi - Zhuangzi

The Structure of Scientific Revolutions - Thomas Kuhn

Hegemony or Survival - Noam Chomsky

Reinforcement Learning: An Introduction - Richard S. Sutton and Andrew G. Barto

Gödel, Escher, Bach: an Eternal Golden Braid - Douglas Hofstadter

Structure and Interpretation of Computer Programs - Harold Abelson and Gerald Sussman with Julie Sussman

The Feynman Lectures on Physics - Richard P. Feynman, Robert B. Leighton, Matthew Sands

Republic - Plato

Tao Te Ching - Laozi

Shorter Works

A Psalm of Life - Henry Wadsworth Longfellow

You and Your Research - Richard Hamming

Building Machines that Think and Learn Like People - Brendan M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum, Samuel J. Gershman

Steps Toward Artificial Intelligence - Marvin Minsky

As We May Think - Vannevar Bush

The Philosophy of Composition - Edgar Allan Poe

Others' Reading Lists

Lucas Morales' reading list

MIT Probabilistic Computing Project's reading list

Jürgen Schmidhuber's recommended readings

Gerry Sussman's reading list

Marcus Hutter's reading list

website template credits