Training products of experts by minimizing contrastive divergence
Neural Computation
Restricted Boltzmann machines for collaborative filtering
Proceedings of the 24th international conference on Machine learning
Hi-index | 0.00 |
The significant advances in artificial neural network research during the last two decades has rendered neural network models well established data analysis techniques. In this paper we examine the performance of a number of neural network models when applied to the Netflix Prize dataset, which is a large scale (more than 100 million training patterns) high-dimensional, and very sparse dataset. Our study comprises of the combination of different neural network approaches that are presented in the main part of the paper.