Proceedings ArticleDOI
A BP Neural Network Model Based on Genetic Algorithm for Comprehensive Evaluation
Xin Sun,Qiongxin Liu,Lei Zhang +2 more
- pp 1-5
Reads0
Chats0
TLDR
A hybrid neural network based on the combination of GA and BP algorithms is proposed, which made fully use of GA's global searching to improve the learning ability of BP neural network.Abstract:
BP algorithm can be applied in comprehensive evaluation. A hybrid neural network based on the combination of GA and BP algorithms is proposed. The algorithm made fully use of GA's global searching to improve the learning ability of BP neural network. Then, the method is used in comprehensive evaluation, which the genetic algorithm can improve the weights of the neural network and enhance the training precision of the neural network. The experimental results show that the method is valid and feasible.read more
Citations
More filters
Journal ArticleDOI
Artificial Neural Network Weight Optimization: A Review
TL;DR: This paper reviews the implementation of meta-heuristic algorithms in ANNs’ weight optimization by studying their advantages and disadvantages giving consideration to some meta- heuristic members such as Genetic algorithim, Particle Swarm Optimization and recently introduced meta-Heuristic algorithm called Harmony Search Algorithm (HSA).
Proceedings ArticleDOI
A novel quantization parameter estimation model based on neural network
TL;DR: A QP prediction scheme, which use artificial neural network (ANN) model combining with H.264 rate-distortion mode improves QP forecast in H.246 encoder and shows less Peak Signal-to-Noise Ratio fluctuation and same Rate-Distortion performance, using proposed scheme instead of quantization model in JM14.2 reference software.
Journal ArticleDOI
Designing stable neural identifier based on Lyapunov method
TL;DR: This paper suggests adaptive gradient descent algorithm with stable learning laws for modified dynamic neural network (MDNN) and studies the stability of this algorithm.
Journal ArticleDOI
Near Optimal Convergence of Back-Propagation Method using Harmony Search Algorithm
TL;DR: Three training algorithms namely Back-Propagation Algorithm, Harmony Search Algorithm and hybrid BP and HSA called BPHSA are employed for the supervised training of Multi-Layer Perceptron feed forward type of Neural Networks (NNs) by giving special attention to hybrid B PHSA.
Proceedings ArticleDOI
An estimation method of inner temperature distribution of TWT slow-wave structure with GA-BP neural network model
TL;DR: In this article, an estimation method for inner temperature distribution of slow-wave structure is proposed without placing temperature sensors inside the traveling wave tube, based on body temperatures, with Genetic BP Neural Network solving the thermodynamic parameters of the thermal model.
References
More filters
Journal ArticleDOI
An introduction to neural computing
TL;DR: A brief survey of the motivations, fundamentals, and applications of artificial neural networks, as well as some detailed analytical expressions for their theory.
Journal ArticleDOI
A methodology to explain neural network classification
Raphaël Féraud,Fabrice Clérot +1 more
TL;DR: A methodology to explain the classification obtained by a multilayer perceptron is proposed and a saliency measurement is introduced and defined allowing the selection of relevant variables allowing an interpretation of the neural network classifier to be built.
Proceedings ArticleDOI
A neural network model for the decision-making process based on AHP
TL;DR: A neural network model of the decision-making process based on the analytic network process by T. L. Saaty (2001) is proposed and works effectively in more practical situations where the authors cannot give the precise information or all the information necessary to make the decision.
Journal Article
Neural Network Training Algorithm Based on Particle Swarm Optimization
TL;DR: A training algorithm for neural network based on particle swarm optimization was investigated and showed that the training algorithm based on PSO is a good one with strong competitiveness.
Journal Article
Modeling of Supply Chain Vendor Selecting System Based on AHP-BP Algorithm and Its Application
TL;DR: The results show that this model is a simple way to deal with vendor selecting problem and makes the selecting result more objective and can be applied in different types of industries.