Using information fractal dimension as temperature in restricted Boltzmann Machine

Abstract

Contrastive Divergence (CD) has shown success in estimating the parameters of Markov Random Fields. Restricted Boltzmann Machine (RBM) updates weights of RBM architecture using CD to minimize the reconstruction error. Minimization of CD is fundamentally equivalent of finding the self-similarity among the training data and the estimated data. However, this… (More)
DOI: 10.1109/IJCNN.2017.7966133

Topics

8 Figures and Tables

Cite this paper

@article{Khan2017UsingIF, title={Using information fractal dimension as temperature in restricted Boltzmann Machine}, author={Muhammad Salman Khan and Sana Siddiqui and Ken Ferens}, journal={2017 International Joint Conference on Neural Networks (IJCNN)}, year={2017}, pages={2290-2297} }