Shortening Time Required for Adaptive Structural Learning Method of Deep Belief Network with Multi-Modal Data Arrangement

TL;DR

This paper proposes a data arrangement modification in the adaptive structural learning of Deep Belief Networks for multi-modal data, which reduces the training time by reorganizing hidden neurons based on input-output pattern similarity.

Contribution

It introduces a novel data arrangement method that reorganizes hidden neurons according to pattern similarity, leading to faster DBN learning for multi-modal data.

Findings

Reduced training time for DBN with data rearrangement

Effective reorganization based on input-output pattern similarity

Improved learning efficiency in multi-modal data processing

Abstract

Recently, Deep Learning has been applied in the techniques of artificial intelligence. Especially, Deep Learning performed good results in the field of image recognition. Most new Deep Learning architectures are naturally developed in image recognition. For this reason, not only the numerical data and text data but also the time-series data are transformed to the image data format. Multi-modal data consists of two or more kinds of data such as picture and text. The arrangement in a general method is formed in the squared array with no specific aim. In this paper, the data arrangement are modified according to the similarity of input-output pattern in Adaptive Structural Learning method of Deep Belief Network. The similarity of output signals of hidden neurons is made by the order rearrangement of hidden neurons. The experimental results for the data rearrangement in squared array showed the shortening time required for DBN learning.