A Video Recognition Method by using Adaptive Structural Learning of Long Short Term Memory based Deep Belief Network
This work addresses video recognition, a domain-specific problem, with an incremental improvement over existing LSTM models.
The paper tackles video recognition by proposing an adaptive structural learning method for Long Short-Term Memory based Deep Belief Networks, achieving over 90% prediction accuracy on the Moving MNIST benchmark dataset.
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% predication accuracy for test data).