How Deep Belief Networks operate part2(Machine Learning)
- A Novel Light Field Coding Scheme Based on Deep Belief Network and Weighted Binary Images for Additive Layered Displays(arXiv)
Author : Sally Khaidem, Mansi Sharma
Abstract : Light field display caters to the viewer’s immersive experience by providing binocular depth sensation and motion parallax. Glasses-free tensor light field display is becoming a prominent area of research in auto-stereoscopic display technology. Stacking light attenuating layers is one of the approaches to implement a light field display with a good depth of field, wide viewing angles and high resolution. This paper presents a compact and efficient representation of light field data based on scalable compression of the binary represented image layers suitable for additive layered display using a Deep Belief Network (DBN). The proposed scheme learns and optimizes the additive layer patterns using a convolutional neural network (CNN). Weighted binary images represent the optimized patterns, reducing the file size and introducing scalable encoding. The DBN further compresses the weighted binary patterns into a latent space representation followed by encoding the latent data using an h.254 codec. The proposed scheme is compared with benchmark codecs such as h.264 and h.265 and achieved competitive performance on light field data.
2.p-Adic Statistical Field Theory and Deep Belief Networks (arXiv)
Author : W. A. Zúñiga-Galindo
Abstract : In this work we initiate the study of the correspondence between p-adic statistical field theories (SFTs) and neural networks (NNs). In general quantum field theories over a p-adic spacetime can be formulated in a rigorous way. Nowadays these theories are considered just mathematical toy models for understanding the problems of the true theories. In this work we show these theories are deeply connected with the deep belief networks (DBNs). Hinton et al. constructed DBNs by stacking several restricted Boltzmann machines (RBMs). The purpose of this construction is to obtain a network with a hierarchical structure (a deep learning architecture). An RBM corresponds to a certain spin glass, we argue that a DBN should correspond to an ultrametric spin glass. A model of such a system can be easily constructed by using p-adic numbers. In our approach, a p-adic SFT corresponds to a p-adic continuous DBN, and a discretization of this theory corresponds to a p-adic discrete DBN. We show that these last machines are universal approximators. In the p-adic framework, the correspondence between SFTs and NNs is not fully developed. We point out several open problems
