A Video Recognition Method by using Adaptive Structural Learning of Long Short Term Memory based Deep Belief Network
A Video Recognition Method by using Adaptive Structural Learning of Long Short Term Memory based Deep Belief Network
复制标题
DOI：
10.1109/iwcia47330.2019.8955036
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
Shin Kamada;T. Ichimura
中科院分区：
文献类型：
--
作者：
Shin Kamada;T. Ichimura
深度学习构建深度架构，如多层人工神经网络，以有效地表示输入模式的多个特征。深度信念网络（DBN）的自适应结构学习方法可以在训练过程中搜索最优网络结构的同时实现高分类能力。该方法通过神经元生成-湮灭算法找到约束玻尔兹曼机（RBM）的最优隐层神经元数目，对给定的输入数据进行训练，然后通过层生成算法在DBN中生成新的层，实现数据的深层表示。此外，利用LSTM（长短期记忆）的思想，将自适应RBM和自适应DBN的学习算法扩展到时间序列分析中。在本文中，我们提出的预测方法被应用到移动MNIST，这是一个基准数据集的视频识别。由于视频包含丰富的视觉信息源，因此我们在视频识别研究领域面临着揭示我们所提出的方法的挑战。与LSTM模型相比，我们的方法表现出更高的预测性能（测试数据的预测准确率超过90%）。
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).