Generalizable Features From Unsupervised Learning
This work addresses the challenge of physical intuition and generalization in AI, offering an incremental approach to enhancing machine learning models for reasoning tasks.
The paper tackled the problem of improving generalization to unseen scenarios by using unsupervised learning to extract features from video sequences of block towers, demonstrating that these features support stability prediction for configurations outside the training distribution.
Humans learn a predictive model of the world and use this model to reason about future events and the consequences of actions. In contrast to most machine predictors, we exhibit an impressive ability to generalize to unseen scenarios and reason intelligently in these settings. One important aspect of this ability is physical intuition(Lake et al., 2016). In this work, we explore the potential of unsupervised learning to find features that promote better generalization to settings outside the supervised training distribution. Our task is predicting the stability of towers of square blocks. We demonstrate that an unsupervised model, trained to predict future frames of a video sequence of stable and unstable block configurations, can yield features that support extrapolating stability prediction to blocks configurations outside the training set distribution