Paper

Modeling documents with a Deep Boltzmann Machine

We introduce a type of Deep Boltzmann Machine (DBM) that is suitable for extracting distributed semantic representations from a large unstructured collection of documents. We overcome the apparent difficulty of training a DBM with judicious parameter tying. This enables an efficient pretraining algorithm and a state initialization scheme for fast inference. The model can be trained just as efficiently as a standard Restricted Boltzmann Machine. Our experiments show that the model assigns better log probability to unseen data than the Replicated Softmax model. Features extracted from our model outperform LDA, Replicated Softmax, and DocNADE models on document retrieval and document classification tasks. 1

http://www.cs.toronto.edu/~rsalakhu/papers/uai13.pdfPublished 2013-08-11Paper link

Authors: Nitish Srivastava · Ruslan Salakhutdinov · Geoffrey E. Hinton

Topics

Relevant entities

People

Related coverage

Linked coverage will appear here.

Related events

Linked events will appear here.

Related discussions

Related discussion nodes will appear here.