Understanding Visual Concepts with Continuation Learning

William F. Whitney, Michael Chang, Tejas Kulkarni, Joshua B. Tenenbaum

Abstract: We introduce a neural network architecture and a learning algorithm to produce fac- torized symbolic representations. We propose to learn these concepts by observing consecutive frames, letting all the components of the hidden representation except a small discrete set (gating units) be predicted from previous frame, and let the factors of variation in the next frame be represented entirely by these discrete gated units (corresponding to symbolic representations). We demonstrate the efficacy of our approach on datasets of faces undergoing 3D transformations and Atari 2600 games.

Conflicts: mit.edu