Supervising Unsupervised Learning with Evolutionary Algorithm in Deep Neural Network

TL;DR

This paper introduces an evolutionary algorithm to supervise unsupervised deep neural network training, improving accuracy in document classification by evaluating node fitness and employing a modified Restricted Boltzmann Machine.

Contribution

It presents a novel method combining evolutionary algorithms with unsupervised learning to enhance neural network training and introduces a modified RBM to prevent node degeneration.

Findings

Achieved better accuracy than traditional supervised classifiers.

Demonstrated effectiveness in document classification tasks.

Proposed a new approach for supervising unsupervised learning.

Abstract

A method to control results of gradient descent unsupervised learning in a deep neural network by using evolutionary algorithm is proposed. To process crossover of unsupervisedly trained models, the algorithm evaluates pointwise fitness of individual nodes in neural network. Labeled training data is randomly sampled and breeding process selects nodes by calculating degree of their consistency on different sets of sampled data. This method supervises unsupervised training by evolutionary process. We also introduce modified Restricted Boltzmann Machine which contains repulsive force among nodes in a neural network and it contributes to isolate network nodes each other to avoid accidental degeneration of nodes by evolutionary process. These new methods are applied to document classification problem and it results better accuracy than a traditional fully supervised classifier implemented with linear regression algorithm.