Poster
ICA with Reconstruction Cost for Efficient Overcomplete Feature Learning
Quoc V. Le · Alexandre Karpenko · Jiquan Ngiam · Andrew Y Ng

Wed Dec 14th 05:45 -- 11:59 PM @ None #None

Independent Components Analysis (ICA) and its variants have been successfully used for unsupervised feature learning. However, standard ICA requires an orthonoramlity constraint to be enforced, which makes it dif´Čücult to learn overcomplete features. In addition, ICA is sensitive to whitening. These properties make it challenging to scale ICA to high dimensional data. In this paper, we propose a robust soft reconstruction cost for ICA that allows us to learn highly overcomplete sparse features even on unwhitened data. Our formulation reveals formal connections between ICA and sparse autoencoders, which have previously been observed only empirically. Our algorithm can be used in conjunction with off-the-shelf fast unconstrained optimizers. We show that the soft reconstruction cost can also be used to prevent replicated features in tiled convolutional neural networks. Using our method to learn highly overcomplete sparse features and tiled convolutional neural networks, we obtain competitive performances on a wide variety of object recognition tasks. We achieve state-of-the-art test accuracies on the STL-10 and Hollywood2 datasets.

Author Information

Quoc V. Le (Google)
Alexandre Karpenko (Stanford University)
Jiquan Ngiam (Stanford University)
Andrew Y Ng (Baidu Research)

More from the Same Authors