Paper Info
Title
Learning neural network structures with ant colony algorithms
Abstract
Ant colony optimization (ACO) has been successfully applied to classification, where the aim is to build a model that captures the relationships between the input attributes and the target class in a given domain’s dataset. The constructed classification model can then be used to predict the unknown class of a new pattern. While artificial neural networks are one of the most widely used models for pattern classification, their application is commonly restricted to fully connected three-layer topologies. In this paper, we present a new algorithm, ANN-Miner, which uses ACO to learn the structure of feed-forward neural networks. We report computational results on 40 benchmark datasets for several variations of the algorithm. Performance is compared to the standard three-layer structure trained with two different weight-learning algorithms (back propagation, and the algorithm), and also to a greedy algorithm for learning NN structures. A nonparametric Friedman test is used to determine statistical significance. In addition, we compare our proposed algorithm with NEAT, a prominent evolutionary algorithm for evolving neural networks, as well as three different well-known state-of-the-art classifiers, namely the C4.5 decision tree induction algorithm, the Ripper classification rule induction algorithm, and support vector machines.
Year
DOI
Venue
2015
10.1007/s11721-015-0112-z
Swarm Intelligence
Keywords
Field
DocType
Ant colony optimization (ACO),Machine learning,Pattern classification,Neural networks
Ant colony optimization algorithms,Decision tree,Classification rule,Evolutionary algorithm,Computer science,Artificial intelligence,Artificial neural network,Pattern recognition,Support vector machine,Algorithm,Greedy algorithm,Backpropagation,Machine learning
Journal
Volume
Issue
ISSN
9
4
1935-3812
Citations 
PageRank 
References 
13
0.58
70
Authors
2
Name
Order
Citations
PageRank
Khalid M. Salama116013.09
Ashraf M. Abdelbar224325.43