Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery

Details Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery

2012-01-16

arxiv.org/abs/1201.3382v2

Statistics

Machine Learning

Scientific paper

We consider the problem of using a factor model we call {\em spike-and-slab sparse coding} (S3C) to learn features for a classification task. The S3C model resembles both the spike-and-slab RBM and sparse coding. Since exact inference in this model is intractable, we derive a structured variational inference procedure and employ a variational EM training algorithm. Prior work on approximate inference for this model has not prioritized the ability to exploit parallel architectures and scale to enormous problem sizes. We present an inference procedure appropriate for use with GPUs which allows us to dramatically increase both the training set size and the amount of latent factors. We demonstrate that this approach improves upon the supervised learning capabilities of both sparse coding and the ssRBM on the CIFAR-10 dataset. We evaluate our approach's potential for semi-supervised learning on subsets of CIFAR-10. We demonstrate state-of-the art self-taught learning performance on the STL-10 dataset and use our method to win the NIPS 2011 Workshop on Challenges In Learning Hierarchical Models' Transfer Learning Challenge.

Affiliated with

Also associated with

No associations

Rating

Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-96379