Why Does Unsupervised Pre-training Help Deep Learning?

Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtained in several areas, mostly on vision and language data sets. The best results obtained on supervised learning tasks involve an unsupervised learning component, usually in an unsupervised pre-training phase. Even though these new algorithms have enabled training deep models, many questions remain as to the nature of this difficult learning problem. The main question investigated here is the following: how does unsupervised pre-training work? Answering this questions is important if learning in deep architectures is to be further improved. We propose several explanatory hypotheses and test them through extensive simulations. We empirically show the influence of pre-training with respect to architecture depth, model capacity, and number of training examples. The experiments confirm and clarify the advantage of...

• Type: Journal
• Year: 2010
• Where: JMLR
• Authors: Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, Pierre-Antoine Manzagol, Pascal Vincent, Samy Bengio
• Keywords: Deep Architectures, JMLR 2010, Unsupervised Pre-training, Unsupervised Pre-training Phase