Published on Wed Jul 11 2018

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

Shin Kamada, Takumi Ichimura

Deep Learning performed good results in the field of image recognition. Data arrangement are modified according to similarity of input-output pattern in Adaptive Structural Learning method. The similarity of output signals of hidden neurons is made by the order rearrangement of hidden neurons.

0
0
0
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.

Thu Nov 19 2015
Machine Learning
Faster method for Deep Belief Network based Object classification using DWT
Deep Belief Network (DBN) requires large, multiple hidden layers with high number of hidden units. This implies more training time as well as computational complexity. By integrating DBN with Discrete Wavelet Transform (DWT), both training time and computational complexity can be reduced.
0
0
0
Tue Jul 10 2018
Neural Networks
An Adaptive Learning Method of Deep Belief Network by Layer Generation Algorithm
Deep Belief Network (DBN) has a deep architecture that represents multiple features of input patterns hierarchically. A traditional RBM or DBN model cannot change its structure during the learning phase. Our proposed adaptive learning method can discover the optimal number of hidden neurons and weights according to the input space.
0
0
0
Fri Dec 20 2013
Neural Networks
Deep Belief Networks for Image Denoising
Deep Belief Networks (DBNs) are effective tools for feature representation and extraction. DBNs can be used in numerous aspects of Machine Learning such as image denoising. In this paper, we propose a novel method for imageDenoising which relies on the DBN's ability
0
0
0
Tue Jul 10 2018
Neural Networks
Fine Tuning Method by using Knowledge Acquisition from Deep Belief Network
We developed an adaptive structure learning method of Restricted Boltzmann Machine (RBM) which can generate/annihilate neurons by self-organizing learning method. The adaptive Deep Belief Network(DBN) in the assemble process of pre-trained RBM layer was developed.
0
0
0
Wed Jul 11 2018
Neural Networks
Adaptive Learning Method of Recurrent Temporal Deep Belief Network to Analyze Time Series Data
Adaptive learning method can discover the optimal network structure in Deep Belief Network (DBN) Learning method can construct the network structure with the optimal number of hidden neurons in each Restricted Boltzmann Machine. The network structure can be self-organized according to given input patterns of big data set.
0
0
0
Mon Aug 27 2018
Neural Networks
Adaptive Structural Learning of Deep Belief Network for Medical Examination Data and Its Knowledge Extraction by using C4.5
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)
0
0
0