Artificial Neural Networks Optimization by means of Evolutionary Algorithms

1998 ◽  
pp. 3-12 ◽  
Author(s):  
I. De Falco ◽  
A. Della Cioppa ◽  
P. Natale ◽  
E. Tarantino
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Evolutionary Algorithms ◽  
Artificial Neural ◽  
Neural Networks Optimization

Intelligence Selection System for Honing Parameter Based on Genetics and Artificial Neural Networks

2010 ◽  
Vol 102-104 ◽  
pp. 846-850
Author(s):  
Wen Yu Pu ◽  
Yan Nian Rui ◽  
Lian Sheng Zhao ◽  
Chun Yan Zhang
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Selection System ◽  
Process Data ◽  
Replacement Strategy ◽  
Machining Quality ◽  
Main Factors ◽  
Artificial Neural ◽  
Neural Networks Optimization ◽  
The Relationship

Appropriate selecting of process parameters influences the machining quality greatly. For honing, the main factors are product precision, material components and productivity. In view of this situation, a intelligence selection model for honing parameter based on genetics and artificial neural networks was built by using excellent robustness, fault-tolerance of artificial neural networks optimization process and excellent self-optimum of genetic algorithm. It can simulate the decision making progress of experienced operators, abstract the relationship from process data and machining incidence, realize the purpose of intelligence selection honing parameter through copying, exchanging, aberrance, replacement strategy and neural networks training. Besides, experiment was performed and the results helped optimize the theories model. Both the theory and experiment show the updated level and feasibility of this system.

Evolutionary Approaches for ANNs Design

2011 ◽  
pp. 575-580
Author(s):  
Antonia Azzini ◽  
Andrea G.B. Tettamanzi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Evolutionary Algorithms ◽  
Computational Models ◽  
Artificial Neurons ◽  
Important Research Topic ◽  
Recent Developments ◽  
Evolving System ◽  
Artificial Neural ◽  
Ann Application

Artificial neural networks (ANNs) are computational models, loosely inspired by biological neural networks, consisting of interconnected groups of artificial neurons which process information using a connectionist approach. ANNs are widely applied to problems like pattern recognition, classification, and time series analysis. The success of an ANN application usually requires a high number of experiments. Moreover, several parameters of an ANN can affect the accuracy of solutions. A particular type of evolving system, namely neuro-genetic systems, have become a very important research topic in ANN design. They make up the so-called Evolutionary Artificial Neural Networks (EANNs), i.e., biologicallyinspired computational models that use evolutionary algorithms (EAs) in conjunction with ANNs. Evolutionary algorithms and state-of-the-art design of EANN were introduced first in the milestone survey by Xin Yao (1999), and, more recently, by Abraham (2004), by Cantu-Paz and Kamath (2005), and then by Castellani (2006). The aim of this article is to present the main evolutionary techniques used to optimize the ANN design, providing a description of the topics related to neural network design and corresponding issues, and then, some of the most recent developments of EANNs found in the literature. Finally a brief summary is given, with a few concluding remarks.

Hybridization of multi-objective evolutionary algorithms and artificial neural networks for optimizing the performance of electrical drives

2013 ◽  
Vol 26 (8) ◽  
pp. 1781-1794 ◽  
Author(s):  
Alexandru-Ciprian Zăvoianu ◽  
Gerd Bramerdorfer ◽  
Edwin Lughofer ◽  
Siegfried Silber ◽  
Wolfgang Amrhein ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Evolutionary Algorithms ◽  
Multi Objective ◽  
Electrical Drives ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document