scispace - formally typeset
Search or ask a question
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
More filters
Book ChapterDOI
16 Oct 2016
TL;DR: This research proposes a precise scheme for human face detection using a hybrid neural network based on visual information of the face image sequences and is commenced with estimation of the skin area depending on color components.
Abstract: Human face detection is a key technology in machine vision applications including human recognition, access control, security surveillance and so on. This research proposes a precise scheme for human face detection using a hybrid neural network. The system is based on visual information of the face image sequences and is commenced with estimation of the skin area depending on color components. In this paper we have considered HSV and YCbCr color space to extract the visual features. These features are used to train the hybrid network consisting of a bidirectional associative memory BAM and a back propagation neural network BPNN. The BAM is used for dimensional reduction and the multi-layer BPNN is used for training the facial color features. Our system provides superior performance comparable to the existing methods in terms of both accuracy and computational efficiency. The low computation time required for face detection makes it suitable to be employed in real time applications.
Book ChapterDOI
28 May 2006
TL;DR: This paper proposes hybrid neural networks for large scale Chinese handwritten character recognition that is composed of the self-organizing competitive fuzzy layer and the multi-layer neural network using BP method, connected in cascade.
Abstract: A professional Chinese fax information processing system is designed which has functions to automate incoming fax distribution in a company or institution, read an incoming fax cover sheet and route the fax to the receiver’s email box This paper reports our research as part of an effort to realize such a system and focuses on recognition of the handwritten recipient’s on fax cover pages We propose hybrid neural networks for large scale Chinese handwritten character recognition The network is composed of the self-organizing competitive fuzzy layer and the multi-layer neural network using BP method, connected in cascade The characteristic features of this network structure for Chinese handwritten character recognition are discussed and performances are evaluated on 8208 real world faxes which are taken from one company in 2004, the results of experiments compared to standard neural solutions based on MLP show that the whole system is of reasonable structure and satisfactory performance
Journal Article
TL;DR: An intelligent hybrid scheme for short term electric load forecasting using multilayered perceptrons and a hybrid learning algorithm consisting of unsupervised and supervised learning for feed forward neural network is presented.
Abstract: This paper presents an intelligent hybrid scheme for short term electric load forecasting using multilayered perceptrons. The hybrid neural network uses the membership values of the linguistic properties of the past load and weather parameters and the output of the network is defined as the fuzzy class membership values of theforecasted load. A hybrid learning algorithm consisting of unsupervised and supervised learning. phases is used for training of the feed forward neural network. In the unsupervised learning phase optimal fuzzy membership values of input/output variables are obtained along with the optimal fuzzy logic rules. Kalman filter is used for the supervised learning phase. Extensive tests have been performed on a two-year utility data for the generation of peak and average load profiles in 24 and 168 hours ahead time frame. Results for typical winterand summer months are given to confirm the effectiveness of the hybrid scheme in comparison to standard ANN approach using back propagation algorithm.
Book ChapterDOI
23 Sep 2020
TL;DR: In this article, the expressive power of bithreshold neurons and their application in pattern classification is discussed. And the authors also demonstrate the relation between the representational capability of threshold and bith threshold neurons and propose an improved algorithm for designing an optimized hybrid BNN.
Abstract: The paper deals with the issues concerning the expressive power of bithreshold neurons and their application in pattern classification. First, we study how many Boolean functions of n variables can be computed by using bithreshold neural units. Our approach is based on the application of combinatorial methods in the theory of neural computation. The lower and upper bounds on the number of bithreshold functions are established whose growth orders have the equal leading terms. We also demonstrate the relation between the representational capability of threshold and bithreshold neurons. Our estimations show the measure of the superiority of bithreshold neurons over threshold ones in the case of binary data. Next, we consider the application of bithreshold neurons in the design of multicategory classifiers. The model of a hybrid neural network is introduced whose hidden layer consists of bithreshold neurons and winner-takes-all units. The use of this model allows us to enhance the representational capability of the classifier. We also propose the improved algorithm for designing an optimized hybrid bithreshold network. Finally, we present the simulation results of the network performance when solving the task of the optical recognition of handwritten digits, discuss the influence of the network components on the quality of the classification and suggest the values of the algorithm parameters providing better accuracy of the network.
Book ChapterDOI
01 Jan 2014
TL;DR: Application to real data of two wells located the Algerian Sahara clearly shows that the lithofacies model built by the neural combination is able to give better results than Self Organizing Map.
Abstract: In this paper, a combination between the supervised and unsupervised leanings is used for lithofacies classification from well-logs data The main idea consists of enhancing the Multilayer Perceptron (MLP) learning by the output of the self-organizing map (SOM) neural network Application to real data of two wells located the Algerian Sahara clearly shows that the lithofacies model built by the neural combination is able to give better results than Self Organizing Map

Network Information
Related Topics (5)
Artificial neural network
207K papers, 4.5M citations
89% related
Feature extraction
111.8K papers, 2.1M citations
88% related
Fuzzy logic
151.2K papers, 2.3M citations
85% related
Convolutional neural network
74.7K papers, 2M citations
84% related
Deep learning
79.8K papers, 2.1M citations
83% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20233
20228
2021128
2020119
2019104
201863