Comparing Information-Theoretic Measures of Complexity in Boltzmann Machines

by   Maxinder S. Kanwal, et al.
berkeley college

In the past three decades, many theoretical measures of complexity have been proposed to help understand complex systems. In this work, for the first time, we place these measures on a level playing field, to explore the qualitative similarities and differences between them, and their shortcomings. Specifically, using the Boltzmann machine architecture (a fully connected recurrent neural network) with uniformly distributed weights as our model of study, we numerically measure how complexity changes as a function of network dynamics and network parameters. We apply an extension of one such information-theoretic measure of complexity to understand incremental Hebbian learning in Hopfield networks, a fully recurrent architecture model of autoassociative memory. In the course of Hebbian learning, the total information flow reflects a natural upward trend in complexity as the network attempts to learn more and more patterns.


page 8

page 9


Information Theoretic Sample Complexity Lower Bound for Feed-Forward Fully-Connected Deep Networks

In this paper, we study the sample complexity lower bound of a d-layer f...

A superstatistical formulation of complexity measures

It is discussed how the superstatistical formulation of effective Boltzm...

On the Information Theoretic Distance Measures and Bidirectional Helmholtz Machines

By establishing a connection between bi-directional Helmholtz machines a...

Control of criticality and computation in spiking neuromorphic networks with plasticity

The critical state is assumed to be optimal for any computation in recur...

A Probabilistic Representation of Deep Learning for Improving The Information Theoretic Interpretability

In this paper, we propose a probabilistic representation of MultiLayer P...

Information-Theoretic Measures for Objective Evaluation of Classifications

This work presents a systematic study of objective evaluations of abstai...

The Stochastic complexity of spin models: How simple are simple spin models?

Simple models, in information theoretic terms, are those with a small st...

Please sign up or login with your details

Forgot password? Click here to reset