Topic
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.
Papers published on a yearly basis
Papers
More filters
Patent•
29 Jan 2021
TL;DR: In this article, a dual-channel hybrid neural network was used to extract local features and context semantic features and then the importance of each character or word in the online comment text to emotion classification is calculated by using a part-of-speech attention mechanism, so that the emotion classification accuracy of the comment text is improved.
Abstract: The invention provides an online comment sentiment classification method based on a dual-channel hybrid neural network. The method comprises the following steps: S1, acquiring and preprocessing an online comment text; s2, obtaining a character vector representation and a word vector representation by using a Word2vec tool; s3, constructing a word-level feature extraction channel; s4, constructinga character-level feature extraction channel; s5, splicing the word-level feature matrix Vleft obtained by the word-level feature extraction channel and the character-level feature matrix Vright obtained by the character-level feature extraction channel together to obtain a dual-channel feature matrix V; and S6, performing comment text sentiment polarity classification by utilizing a softmax classifier. According to the method, firstly, local features and context semantic features are extracted by using the hybrid neural network, and then the importance of each character or word in the onlinecomment text to emotion classification is calculated by using a part-of-speech attention mechanism, so that the emotion classification accuracy of the comment text is improved.
2 citations
07 Aug 2006
TL;DR: A modified version of fuzzy min-max (FMM) neural network for feature analysis and face classification and a relevance factor between features and pattern classes is defined to analyze the saliency of features.
Abstract: In this paper, we present a real-time face detection method based on hybrid neural networks. We propose a modified version of fuzzy min-max (FMM) neural network for feature analysis and face classification. A relevance factor between features and pattern classes is defined to analyze the saliency of features. The measure can be utilized for the feature selection to construct an adaptive skin-color filter. The feature extraction module employs a convolutional neural network (CNN) with a Gabor transform layer to extract successively larger features in a hierarchical set of layers. In this paper we first describe the behavior of the proposed FMM model, and then introduce the feature analysis technique for skin-color filter and pattern classifier.
2 citations
17 Jul 2020
TL;DR: A hybrid model of convolutional neural network and long-term and short-term memory network is constructed, which realizes the recognition of speech emotion and is found that the hybrid neural network model is significantly better than that of CNN or LSTM network alone.
Abstract: The main work of this paper is based on the research of psychological counseling and personality analysis algorithms of speech emotions. First, the speech emotion recognition and related work are briefly introduced. Starting from the aspect of deep learning, after researching the relevant neural network architecture, a hybrid model of convolutional neural network and long-term and short-term memory network is constructed, which realizes the recognition of speech emotion. We used the CASIA Chinese data set, which contains 7,200 speeches to train and test the model. The recognition rate of the model on this data set reached 0.8365, showing a good recognition function. At the same time, the natural speech data set collected by the experiment was tested in the experiment, which proved that the model has certain recognition ability. In addition, through comparative experiments, we found that the hybrid neural network model is significantly better than that of CNN or LSTM network alone. Finally, according to the Five-Factor Model, we conducted a personality analysis.
2 citations
TL;DR: In this paper, the authors explored several deep learning methods, such as multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM), and builds combinations of those three architectures.
Abstract: Sentiment analysis of short texts is challenging because of its limited context of information. It becomes more challenging to be done on limited resource language like Bahasa Indonesia. However, with various deep learning techniques, it can give pretty good accuracy. This paper explores several deep learning methods, such as multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM), and builds combinations of those three architectures. The combinations of those three architectures are intended to get the best of those architecture models. The MLP accommodates the use of the previous model to obtain classification output. The CNN layer extracts the word feature vector from text sequences. Subsequently, the LSTM repetitively selects or discards feature sequences based on their context. Those advantages are useful for different domain datasets. The experiments on sentiment analysis of short text in Bahasa Indonesia show that hybrid models can obtain better performance, and the same architecture can be directly used in another domain-specific dataset.
2 citations
07 Aug 2002
TL;DR: A hybrid that achieves very accurate control in both stable an unstable operating regions of a simulated bioreactor using a neural network and conventional controllers is proposed.
Abstract: We combine neural network and conventional controllers to form a hybrid that achieves very accurate control in both stable an unstable operating regions of a simulated bioreactor. The neural network handles nonlinearity and generalizes to cover both regions. The conventional controller eliminates the offset error incurred by generalization.
2 citations