On the Information Theoretic Distance Measures and Bidirectional Helmholtz Machines

07/16/2018
by   Mahdi Azarafrooz, et al.
0

By establishing a connection between bi-directional Helmholtz machines and information theory, we propose a generalized Helmholtz machine. Theoretical and experimental results show that given shallow architectures, the generalized model outperforms the previous ones substantially.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/14/2021

BiGCN: A Bi-directional Low-Pass Filtering Graph Neural Network

Graph convolutional networks have achieved great success on graph-struct...
research
06/29/2017

Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines

In the past three decades, many theoretical measures of complexity have ...
research
04/07/2020

A System of Billiard and Its Application to Information-Theoretic Entropy

In this article, we define an information-theoretic entropy based on the...
research
09/09/2021

Gradual (In)Compatibility of Fairness Criteria

Impossibility results show that important fairness measures (independenc...
research
11/11/2015

Unifying distillation and privileged information

Distillation (Hinton et al., 2015) and privileged information (Vapnik & ...
research
12/03/2015

Adjusting for Chance Clustering Comparison Measures

Adjusted for chance measures are widely used to compare partitions/clust...

Please sign up or login with your details

Forgot password? Click here to reset