A hybrid neural learning algorithm using evolutionary learning and derivative free local search method
- Authors: Ghosh, Ranadhir , Yearwood, John , Ghosh, Moumita , Bagirov, Adil
- Date: 2006
- Type: Text , Journal article
- Relation: International Journal of Neural Systems Vol. 16, no. 3 (2006), p. 201-213
- Full Text: false
- Reviewed:
- Description: In this paper we investigate a hybrid model based on the Discrete Gradient method and an evolutionary strategy for determining the weights in a feed forward artificial neural network. Also we discuss different variants for hybrid models using the Discrete Gradient method and an evolutionary strategy for determining the weights in a feed forward artificial neural network. The Discrete Gradient method has the advantage of being able to jump over many local minima and find very deep local minima. However, earlier research has shown that a good starting point for the discrete gradient method can improve the quality of the solution point. Evolutionary algorithms are best suited for global optimisation problems. Nevertheless they are cursed with longer training times and often unsuitable for real world application. For optimisation problems such as weight optimisation for ANNs in real world applications the dimensions are large and time complexity is critical. Hence the idea of a hybrid model can be a suitable option. In this paper we propose different fusion strategies for hybrid models combining the evolutionary strategy with the discrete gradient method to obtain an optimal solution much quicker. Three different fusion strategies are discussed: a linear hybrid model, an iterative hybrid model and a restricted local search hybrid model. Comparative results on a range of standard datasets are provided for different fusion hybrid models. © World Scientific Publishing Company.
- Description: C1
- Description: 2003001712
A fully automated breast cancer recognition system using discrete-gradient based clustering and multi category feature selection
- Authors: Ghosh, Ranadhir , Ghosh, Moumita , Yearwood, John
- Date: 2005
- Type: Text , Journal article
- Relation: Journal of Advanced Computational Intelligence and Intelligent Informatics Vol. 9, no. 3 (2005), p. 244-256
- Full Text: false
- Reviewed:
- Description: Advances in machine intelligence have provided a whole new window of opportunities in medical research. Building a fully automated computer aided diagnostic system for digital mammograms is just one of them. Given some success with semi-automated systems earlier, a fully automated CAD system is just another step forward. A proper combination of a feature selection model and a classifier for those areas of a mammogram marked by radiologists has been very successful. However a fully automated system with only two modules is a time consuming process as the suspicious areas in a mammogram can be quite small when compared to the whole image. Thus an additional clustering process can help in reducing the time complexity of the overall process. In this paper we propose a fast clustering process to identify suspicious areas. Another novelty of this paper is a multi-category feature selection approach. The choice of features to represent the patterns affects several aspects of pattern recognition problems such as accuracy, required learning time and the required number of samples. In this paper we propose a hybrid canonical based feature extraction technique as a combination of an evolutionary algorithm based classifier with a feed forward MLP model.
- Description: C1
- Description: 2003001358
Modular neural network design for the problem of alphabetic character recognition
- Authors: Ferguson, Brent , Ghosh, Ranadhir , Yearwood, John
- Date: 2005
- Type: Text , Journal article
- Relation: International Journal of Pattern Recognition and Artificial Intelligence Vol. 19, no. 2 (Mar 2005), p. 249-269
- Full Text: false
- Reviewed:
- Description: This paper reports on an experimental approach to nd a modularized articial neural network solution for the UCI letters recognition problem. Our experiments have been carried out in two parts. We investigate directed task decomposition using expert knowledge and clustering approaches to nd the subtasks for the modules of the network. We next investigate processes to combine the modules e ectively in a single decision process. After having found suitable modules through task decomposition we have found through further experimentation that when the modules are combined with decision tree supervision, their functional error is reduced signicantly to improve their combination through the decision process that has been implemented as a small multilayered perceptron. The experiments conclude with a modularized neural network design for this classication problem that has increased learning and generalization characteristics. The test results for this network are markedly better than a single or stand alone network that has a fully connected topology.
- Description: C1
- Description: 2003001355
Some special properties of G A- and LS-based neural learning method
- Authors: Ghosh, Ranadhir
- Date: 2005
- Type: Text , Journal article
- Relation: Journal of Intelligent Systems Vol. 14, no. 4 (2005), p. 289-319
- Full Text: false
- Reviewed:
- Description: Many works in the area of hybrid neural learning algorithms combine global and local based method for artificial neural network. In this paper, we discuss some special properties of a hybrid neural learning algorithm that combines the GA based method with least square based methods such as QR factorization. We look at different types of learning properties of this new hybrid algorithm, such as time complexity, convergence property, and the stability of the algorithm.
- Description: C1
- Description: 2003001361
A fully automated offline handwriting recognition system incorporating rule based neural network validated segmentation and hybrid neural network classifier
- Authors: Ghosh, Moumita , Ghosh, Ranadhir , Verma, Brijesh
- Date: 2004
- Type: Text , Journal article
- Relation: International Journal of Pattern Recognition and Artificial Intelligence Vol. 18, no. 7 (Nov 2004), p. 1267-1283
- Full Text: false
- Reviewed:
- Description: In this paper we propose a fully automated offline handwriting recognition system that incorporates rule based segmentation, contour based feature extraction, neural network validation, a hybrid neural network classifier and a hamming neural network lexicon. The work is based on our earlier promising results in this area using heuristic segmentation and contour based feature extraction. The segmentation is done using many heuristic based set of rules in an iterative manner and finally followed by a neural network validation system. The extraction of feature is performed using both contour and structure based feature extraction algorithm. The classification is performed by a hybrid neural network that incorporates a hybrid combination of evolutionary algorithm and matrix based solution method. Finally a hamming neural network is used as a lexicon. A benchmark dataset from CEDAR has been used for training and testing- Author
- Description: C1
- Description: 2003000867
Connection topologies for combining genetic and least square methods for neural learning
- Authors: Ghosh, Ranadhir
- Date: 2004
- Type: Text , Journal article
- Relation: Journal of Intelligent Systems Vol. 13, no. 3 (2004), p. 199-232
- Full Text: false
- Reviewed:
- Description: In the last few years, there have been many works in the area of hybrid neural learning algorithms combining a global and local based method for training artificial neural networks. In this paper, we discuss various connection strategies that can be applied to a special kind of a hybrid neural learning algorithm group, one that combines a genetic algorithm-based method with various least square-based methods like QR factorization. The relative advantages and disadvantages of the different connection types are studied to find a suitable connection topology for combining the two different learning methods. The methodology also finds the optimum number of hidden neurons using a hierarchical combination methodology structure for weights and architecture. We have tested our proposed approach on XOR, 10 bit odd parity, and some other real-world benchmark data sets, such as the hand-writing character dataset from CEDAR, Breast cancer, and Heart Disease from the UCI machine learning repository.
- Description: C1
A hierarchical method for finding optimal architecture and weights using evolutionary least square based learning
- Authors: Ghosh, Ranadhir , Verma, Brijesh
- Date: 2003
- Type: Text , Journal article
- Relation: International Journal of Neural Systems Vol. 13, no. 1 (2003), p. 13-24
- Full Text: false
- Reviewed:
- Description: In this paper, we present a novel approach of implementing a combination methodology to find appropriate neural network architecture and weights using an evolutionary least square based algorithm (GALS).1 This paper focuses on aspects such as the heuristics of updating weights using an evolutionary least square based algorithm, finding the number of hidden neurons for a two layer feed forward neural network, the stopping criterion for the algorithm and finally some comparisons of the results with other existing methods for searching optimal or near optimal solution in the multidimensional complex search space comprising the architecture and the weight variables. We explain how the weight updating algorithm using evolutionary least square based approach can be combined with the growing architecture model to find the optimum number of hidden neurons. We also discuss the issues of finding a probabilistic solution space as a starting point for the least square method and address the problems involving fitness breaking. We apply the proposed approach to XOR problem, 10 bit odd parity problem and many real-world benchmark data sets such as handwriting data set from CEDAR, breast cancer and heart disease data sets from UCI ML repository. The comparative results based on classification accuracy and the time complexity are discussed.
- Description: 2003004100