Summary
Artificial Neural Networks are commonly used in pattern classification, function approximation, optimization, pattern matching, machine learning and associative memories. They are currently being an alternative to traditional statistical methods for mining data sets in order to classify data. Artificial Neural Networks are well-established technology for solving prediction and classification problems, using training and testing data to build a model. However, the success of the networks is highly dependent on the performance of the training process and hence the training algorithm. In this paper, we applied the Artificial Bee Colony (ABC) Optimization Algorithm on training feed-forward neural networks to classify different data sets which are widely used in the machine learning community. The performance of the ABC algorithm is investigated on benchmark classification problems from classification area and the results are compared with the other well-known conventional and evolutionary algorithms. The results indicate that ABC algorithm can efficiently be used on training feed-forward neural networks for the purpose of pattern classification.
See the full content of this document
Extract
Neural Networks Training by Artificial Bee Colony Algorithm On Pattern Classification
1. Introduction
Artificial Neural Networks (ANNs) are being successfully applied to solving problems in pattern classification, function approximation, optimization, pattern matching and associative memories [1, 2]. Broad applicable areas of artificial neural networks, pattern recognition is one of the most important applications in such problems: speech synthesis, diagnostic problems, medicine, finance, robotic control, signal processing, computer vision and many other problems that fall under the category of pattern recognition [3]. Among many different neural network classifiers, the multilayer feed- forward networks have been mainly used for solving classification tasks, due to their well-known universal approximation capabilities [4].The success of neural networks largely depends on their architecture, their training algorithm, and the choice of features used in training. All these make design of artificial neural networks a difficult optimization problem [5] . Researchers have been studying to train the networks by choosing suitable architecture and/or training algorithm and/or the transfer functions and/or finding the weights and the biases based on some training data [6, 7, 8, 9, 10, H]. In many approaches, the topology and transfer functions are held fixed, and the space of possible networks is spanned by all possible values of the weights and biases [12]...See the full content of this document
Sponsored links
