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.

Semi-empirical MOCVD modeling using neural networks

Abstract: Metal-organic chemical vapor deposition (MOCVD) is an important fabrication process used to grow thin epitaxial films on solid substrates. The development of an accurate and efficient model for this technique is therefore quite desirable from a manufacturing standpoint. In this paper, semi-empirical modeling of TiO2 film growth by MOCVD using a hybrid neural network is introduced. This hybrid model combines the best aspects of physical models and purely empirical methods. The model was constructed by characterization of the deposition rate of TiO2 films under various operating conditions. A modified back-propagation neural network was trained on the experimental data to determine the value of three critical unknown parameters of the physical model. Using this approach, comparison with measured data showed that the hybrid model is capable of predicting the TiO2 deposition rate with a high degree of accuracy.© (1994) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Hybrid neural network recommendation system based on collaborative filtering model

Abstract: The invention discloses a hybrid neural network recommendation system based on a collaborative filtering model. The system comprises a data preprocessing module, a hybrid neural collaborative filtering module, a score prediction module, a recommendation module and a database, and is characterized in that the data preprocessing module acquires original data from the database and converts the original data into a matrix form. The hybrid neural collaborative filtering module obtains a probability value of user scoring through a mode of training a plurality of models at the same time. The score prediction module outputs a final score prediction value through combination of the hybrid neural collaborative filtering module and generalized matrix decomposition, and finally stores the score prediction value as a score prediction result in a database. And the recommendation module uses the score prediction result calculated by the score prediction module to recommend to the user through sortingthe evaluation indexes. The hybrid neural network of different structures is utilized, more neural network layers are used, the prediction accuracy is remarkably improved, and the obtained information is more diversified.

Neural network for visual search classification

Abstract: Visual search describes the process of how the eyes move in a visual field in order to acquire a target. Visual search needs to be quantified to improve future search strategies. This paper describes a hybrid neural network used to perform visual search classification. The neural network consists of a Learning vector quantization network (LVQ) and a single layer perceptron. The objective of this neural network is to classify the various human visual search patterns into predetermined classes. The classes signify the different search strategies used by individuals to scan the same target pattern. The input search patterns are quantified with respect to an ideal search pattern, determined by the user. A supervised learning rule, Learning vector quantization1 (lvq1) is used to train the network.

A new hybrid neural network classifier based on adaptive neuron and multiplicative neuron

Abstract: Neural network (NN) classifiers are very popular tools for solving classification tasks. Mostly known NN classifier is a multilayer perceptron (MLP). Although MLP has a good correct classification ratio, its structure could be very complex and network training may work for a long time. Pi-sigma NN (PSNN) is higher-order NN (HONN), which used higher-order correlations among the input components to establish a HONN, and the PSNN utilizes the product of neurons as the output units. By contrast with MLP and PSNN, single multiplicative neuron (SMN) is simple concerning its structure and mathematical model. The absence of the hidden layer(s) could be an advantage for easy implementation, and the mathematical model can be easily interpreted. In this paper, we propose a new hybrid NN classifier based on simple adaptive neurons and SMN which form the SMN as a whole, where input units are constituted by adaptive neurons. In contrast with conventional NN, our proposed classifier can use fewer learning parameters. To train this network, we use a modified particle swarm optimization (MPSO) algorithm. For the investigation of the generalization capability of the proposed classifier, we compare this method to other NN classifiers: MLP and PSNN together with other classification procedure classifiers.