A Video Recognition Method by using Adaptive Structural Learning of Long Short Term Memory based Deep Belief Network

by   Shin Kamada, et al.
Prefectural University of Hiroshima

Deep learning builds deep architectures such as multi-layered artificial neural networks to effectively represent multiple features of input patterns. The adaptive structural learning method of Deep Belief Network (DBN) can realize a high classification capability while searching the optimal network structure during the training. The method can find the optimal number of hidden neurons of a Restricted Boltzmann Machine (RBM) by neuron generation-annihilation algorithm to train the given input data, and then it can make a new layer in DBN by the layer generation algorithm to actualize a deep data representation. Moreover, the learning algorithm of Adaptive RBM and Adaptive DBN was extended to the time-series analysis by using the idea of LSTM (Long Short Term Memory). In this paper, our proposed prediction method was applied to Moving MNIST, which is a benchmark data set for video recognition. We challenge to reveal the power of our proposed method in the video recognition research field, since video includes rich source of visual information. Compared with the LSTM model, our method showed higher prediction performance (more than 90


page 1

page 5


An Object Detection by using Adaptive Structural Learning of Deep Belief Network

Deep learning forms a hierarchical network structure for representation ...

Deep Adaptive Network: An Efficient Deep Neural Network with Sparse Binary Connections

Deep neural networks are state-of-the-art models for understanding the c...

Deep Learning to Attend to Risk in ICU

Modeling physiological time-series in ICU is of high clinical importance...

Automatic Extraction of Road Networks from Satellite Images by using Adaptive Structural Deep Belief Network

In our research, an adaptive structural learning method of Restricted Bo...

Deep-learning-based prediction of nanoparticle phase transitions during in situ transmission electron microscopy

We develop the machine learning capability to predict a time sequence of...

Deep Embedding for Spatial Role Labeling

This paper introduces the visually informed embedding of word (VIEW), a ...

Please sign up or login with your details

Forgot password? Click here to reset