Hybrid neural network

About: Hybrid neural network is a research topic. Over the lifetime, 1305 publications have been published within this topic receiving 18223 citations.

Stock Volatility Prediction by Hybrid Neural Network

Abstract: Stock price volatility forecasting is a hot topic in time series prediction research, which plays an important role in reducing investment risk. However, the trend of stock price not only depends on its historical trend, but also on its related social factors. This paper proposes a hybrid time-series predictive neural network (HTPNN) that combines the effection of news. The features of news headlines are expressed as distributed word vectors which are dimensionally reduced to optimize the efficiency of the model by sparse automatic encoders. Then, according to the timeliness of stocks, the daily K-line data is combined with the news. HTPNN captures the potential law of stock price fluctuation by learning the fusion feature of news and time series, which not only retains the effective information of news and stock data, but also eliminates the redundant information of the text. Compared with the state-of-the-art methods, our method combines more abundant stock characteristics and has more advantages in running speed. Besides, the accuracy is averagely improved by nearly 5%.

Hybrid neural network for pattern recognition

Abstract: A system and a method for recognizing patterns comprises a first stage forxtracting features from inputted patterns and for providing topological representations of the characteristics of the inputted patterns and a second stage for classifying and recognizing the inputted patterns. The first stage comprises two one-layer neural networks and the second stage comprises a feedforward two-layer neural network. Supplying signals representative of a set of inputted patterns to the input layers of the first and second neural networks, training the first and second neural networks using a competitive learning algorithm, and generating topological representations of the input patterns using the first and second neural networks The method further comprises providing a third neural network for classifying and recognizing the inputted patterns and training the third neural network with a back-propagation algorithm so that the third neural network recognizes at least one interested pattern.

Visual Scene-aware Hybrid Neural Network Architecture for Video-based Facial Expression Recognition

Abstract: With rapid development of deep learning, facial expression recognition (FER) technology has made considerable progress recently. However, since conventional FER techniques are mainly designed and learned for videos which are artificially acquired in a limited environment, they may not operate robustly on videos acquired in a wild environment. To solve this problem, this paper proposes a scene-aware hybrid neural network (NN) having a novel combination of three-dimensional (3D) convolutional NN (CNN), 2D CNN and recurrent NN (RNN). The characteristics of the proposed network are as follows. First, we extract video-based global features and frame-based local features at the same time. In detail, the latent features containing the overall visual scene of a given video are extracted by 3D CNN with auxiliary classifier, and fine-tuned 2D CNN is adopted to extract latent features containing small details from each frame. Second, RNN not only performs temporal domain learning, but also feature-wise fuses two latent features extracted from the networks. For effective fusion, we also present three RNN schemes. Third, the proposed network, in which the above-mentioned methods collaborate, works very robust in a wild environment as well as in a limited environment. Extensive experiments show that the proposed network provides an average accuracy of 49.9% for AFEW dataset, i.e., a representative wild dataset, and an amazing accuracy of 98.2% for another CK+ dataset. We also show that the proposed network outperforms the state-of-the-art network(s).