Adaptive Structural Learning of Deep Belief Network for Medical Examination Data and Its Knowledge Extraction by using C4.5

TL;DR

This paper presents an adaptive structural learning method for Deep Belief Networks that optimizes hidden layer structure for medical data, achieving high accuracy and extracting interpretable rules for early cancer detection.

Contribution

It introduces a neuron generation-annihilation algorithm for adaptive structure learning in DBNs and applies it to medical data for improved cancer prediction and knowledge extraction.

Findings

Achieved 99.8% training accuracy and 95.5% test accuracy.

Successfully extracted IF-THEN rules for early cancer detection.

Demonstrated improved performance over traditional DBN.

Abstract

Deep Learning has a hierarchical network architecture to represent the complicated feature of input patterns. The adaptive structural learning method of Deep Belief Network (DBN) has been developed. The method can discover an optimal number of hidden neurons for given input data in a Restricted Boltzmann Machine (RBM) by neuron generation-annihilation algorithm, and generate a new hidden layer in DBN by the extension of the algorithm. In this paper, the proposed adaptive structural learning of DBN was applied to the comprehensive medical examination data for the cancer prediction. The prediction system shows higher classification accuracy (99.8% for training and 95.5% for test) than the traditional DBN. Moreover, the explicit knowledge with respect to the relation between input and output patterns was extracted from the trained DBN network by C4.5. Some characteristics extracted in the form of IF-THEN rules to find an initial cancer at the early stage were reported in this paper.