Learn More
Restricted Boltzmann Machines (RBM) are energy-based models that are successfully used as generative learning models as well as crucial components of Deep Belief Networks (DBN). The most successful training method to date for RBMs is the Contrastive Divergence method. However, Contrastive Divergence is inefficient when the number of features is very high(More)
Deep learning is a popular field that encompasses a range of multi-layer connectionist techniques. While these techniques have achieved great success on a number of difficult computer vision problems, the representation biases that allow this success have not been thoroughly explored. In this paper, we examine the hypothesis that one strength of many deep(More)
Current trust models for social networks commonly rely on explicit voting mechanisms where individuals vote for each other as a form of trust statement. However, there is a wealth of information about individuals beyond trust voting in emerging web based social networks. Incorporating sources of evidence into trust models for social networks has not been(More)
Deep learning has recently gained popularity in many machine learning applications, but a theoretical grounding for the strengths, weaknesses, and implicit biases of various deep learning methods is still a work in progress. Here, we analyze the role of spatial locality in Deep Belief Networks (DBN) and show that spatially local information is lost through(More)
We develop a Partitioned Restricted Boltzmann Machine (PRBM) for classification. We demonstrate that this method provides both speed and accuracy. Specifically, because it is partitioned into smaller RBMs, all available data can be used for training, and individual RBMs can be trained in parallel. Moreover, as the number of dimensions increases, the number(More)
This project report has been read by each member of the thesis committee and has been found to be satisfactory regarding content, English usage, format, citation, bibliographic style, and consistency and is ready for submission to The Graduate School. In presenting this project report in partial fulfillment of the requirements for a master's degree at(More)
  • 1