Generalizable Features From Unsupervised Learning

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

[1]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Honglak Lee,et al.  Action-Conditional Video Prediction using Deep Networks in Atari Games , 2015, NIPS.

[3]  Jiajun Wu,et al.  A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding , 2016, CogSci.

[4]  Sergey Levine,et al.  Unsupervised Learning for Physical Interaction through Video Prediction , 2016, NIPS.

[5]  Sergey Levine,et al.  Deep visual foresight for planning robot motion , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[6]  Lucas Theis,et al.  Amortised MAP Inference for Image Super-resolution , 2016, ICLR.

[7]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[8]  Rob Fergus,et al.  Learning Physical Intuition of Block Towers by Example , 2016, ICML.

[9]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

[10]  Yann LeCun,et al.  Deep multi-scale video prediction beyond mean square error , 2015, ICLR.

[11]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[12]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[13]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[14]  J. Stockman.  Pure Reasoning in 12-Month-Old Infants as Probabilistic Inference , 2013 .

[15]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[16]  Gabriel Kreiman,et al.  Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning , 2016, ICLR.

[17]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[18]  Vysoké Učení,et al.  Statistical Language Models Based on Neural Networks , 2012 .

[19]  Xinyun Chen.  Under Review as a Conference Paper at Iclr 2017 Delving into Transferable Adversarial Ex- Amples and Black-box Attacks , 2016 .

[20]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.

[21]  Joshua B. Tenenbaum,et al.  Building machines that learn and think like people , 2016, Behavioral and Brain Sciences.

[22]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[24]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[25]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[26]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[27]  Jitendra Malik,et al.  Learning Visual Predictive Models of Physics for Playing Billiards , 2015, ICLR.

[28]  Nitish Srivastava,et al.  Unsupervised Learning of Video Representations using LSTMs , 2015, ICML.