An Analysis of Single-Layer Networks in Unsupervised Feature Learning
Adam Coates, Andrew Ng, Honglak Lee; JMLR W&CP 15:215-223, 2011.
AbstractA great deal of research has focused on algorithms for learning features from unlabeled data. Indeed, much progress has been made on benchmark datasets like NORB and CIFAR-10 by employing increasingly complex unsupervised learning algorithms and deep models. In this paper, however, we show that several simple factors, such as the number of hidden nodes in the model, may be more important to achieving high performance than the learning algorithm or the depth of the model. Speci?cally, we will apply several o?-the-shelf feature learning algorithms (sparse auto-encoders, sparse RBMs, K-means clustering, and Gaussian mixtures) to CIFAR-10, NORB, and STL datasets using only single-layer networks. We then present a detailed analysis of the e?ect of changes in the model setup: the receptive ?eld size, num- ber of hidden nodes (features), the step-size (“stride”) between extracted features, and the e?ect of whitening. Our results show that large numbers of hidden nodes and dense feature extraction are critical to achieving high performanceso critical, in fact, that when these parameters are pushed to their limits, we achieve state-of-the-art performance on both CIFAR-10 and NORB using only a single layer of features. More surprisingly, our best performance is based on K-means clustering, which is extremely fast, has no hyper-parameters to tune beyond the model structure itself, and is very easy to implement. Despite the simplicity of our system, we achieve accuracy beyond all previously published results on the CIFAR-10 and NORB datasets (79.6% and 97.2% respectively).