Neuronal Correlation: a Central Concept in Neural Network

by   Gaojie Jin, et al.

This paper proposes to study neural networks through neuronal correlation, a statistical measure of correlated neuronal activity on the penultimate layer. We show that neuronal correlation can be efficiently estimated via weight matrix, can be effectively enforced through layer structure, and is a strong indicator of generalisation ability of the network. More importantly, we show that neuronal correlation significantly impacts on the accuracy of entropy estimation in high-dimensional hidden spaces. While previous estimation methods may be subject to significant inaccuracy due to implicit assumption on neuronal independence, we present a novel computational method to have an efficient and authentic computation of entropy, by taking into consideration the neuronal correlation. In doing so, we install neuronal correlation as a central concept of neural network.


page 7

page 9


How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks

This paper studies the novel concept of weight correlation in deep neura...

Improving correlation method with convolutional neural networks

We present a convolutional neural network for the classification of corr...

A Multi-Way Correlation Coefficient

Pearson's correlation is an important summary measure of the amount of d...

Neural Random Projection: From the Initial Task To the Input Similarity Problem

In this paper, we propose a novel approach for implicit data representat...

On Thermodynamic Interpretation of Copula Entropy

Copula Entropy (CE) is a recently introduced concept for measuring corre...

Universal Dependency Analysis

Most data is multi-dimensional. Discovering whether any subset of dimens...

Please sign up or login with your details

Forgot password? Click here to reset