Journal ArticleDOI
Using Genetic Algorithms to Optimize Artificial Neural Networks.
Reads0
Chats0
TLDR
A brief survey on ANNs optimization with GAs, where the superiority of using GAs to optimize ANNs is expressed and the basic principles of ANNs and GAs are introduced.Abstract:
Artificial Neural Networks (ANNs), as a nonlinear and adaptive information processing systems, play an important role in machine learning, artificial intelligence, and data mining. But the performance of ANNs is sensitive to the number of neurons, and chieving a better network performance and simplifying the network topology are two competing objectives. While Genetic Algorithms (GAs) is a kind of random search algorithm which simulates the nature selection and evolution, which has the advantages of good global search abilities and learning the approximate optimal solution without the gradient information of the error functions. This paper makes a brief survey on ANNs optimization with GAs. Firstly, the basic principles of ANNs and GAs are introduced, by analyzing the advantages and disadvantages of GAs and ANNs, the superiority of using GAs to optimize ANNs is expressed. Secondly, we make a brief survey on the basic theories and algorithms of optimizing the network weights, optimizing the network architecture and optimizing the learning rules, and make a discussion on the latest research progresses. At last, we make a prospect on the development trend of the theory.read more
Citations
More filters
Journal ArticleDOI
A novel Clustering based Genetic Algorithm for route optimization
TL;DR: Cl clustering based GA with polygamy and dynamic population control mechanism have been proposed and showed that the proposed algorithm outperforms some of the existing techniques and converged to global solution within few iterations (generations) thus favoring its acceptability for online-realtime applications.
Journal ArticleDOI
Studies on Optimization Algorithms for Some Artificial Neural Networks Based on Genetic Algorithm (GA)
TL;DR: Experiments prove that the network got by the optimizing GA method has a better architecture and stronger classification ability, and the time of constructing the network artificially is saved.
Proceedings ArticleDOI
Genetic Algorithms and Its Application in Software Test Data Generation
TL;DR: A practical model, which utilizes genetic algorithms as searching policy to generate software structural test data, is proposed and the results show that the application of genetic algorithms in software test data generation is more efficient compared with other methods.
Proceedings ArticleDOI
A Decade Survey of Engineering Applications of Genetic Algorithm in Power System Optimization
TL;DR: A state-of-the-art survey of applications of GA technique in engineering with focus on system power optimization using GA in the last decade is presented.
Journal ArticleDOI
Improved Intelligent Method for Traffic Flow Prediction Based on Artificial Neural Networks and Ant Colony Optimization
TL;DR: A prediction method that combining artificial neural networks (ANN) with ant colony optimization (ACO) by exploiting complementary advantages of both approaches, called ANN-ACO, is used, which can be used to forecast real-time traffic flow.
References
More filters
Journal ArticleDOI
A logical calculus of the ideas immanent in nervous activity
Warren S. McCulloch,Walter Pitts +1 more
TL;DR: In this article, it is shown that many particular choices among possible neurophysiological assumptions are equivalent, in the sense that for every net behaving under one assumption, there exists another net which behaves under another and gives the same results, although perhaps not in the same time.
Book
Introduction To The Theory Of Neural Computation
TL;DR: This book is a detailed, logically-developed treatment that covers the theory and uses of collective computational networks, including associative memory, feed forward networks, and unsupervised learning.
Book
Handbook of Genetic Algorithms
TL;DR: This book sets out to explain what genetic algorithms are and how they can be used to solve real-world problems, and introduces the fundamental genetic algorithm (GA), and shows how the basic technique may be applied to a very simple numerical optimisation problem.
Journal ArticleDOI
A logical calculus of the ideas immanent in nervous activity
Warren S. McCulloch,Walter Pitts +1 more
TL;DR: It is shown that many particular choices among possible neurophysiological assumptions are equivalent, in the sense that for every net behaving under one assumption, there exists another net which behaves under the other and gives the same results, although perhaps not in the same time.
Journal ArticleDOI
Evolving artificial neural networks
TL;DR: It is shown, through a considerably large literature review, that combinations between ANNs and EAs can lead to significantly better intelligent systems than relying on ANNs or EAs alone.