NEURAL NETWORK ENGINEERING USING LEARNING AUTOMATA: DETERMINATION OF DESIRED SIZE FOR THREE LAYERS FEED FORWARD NEURAL NETWORKS

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

MEYBODI M.R.; BEYGY H.

Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: Year:2001 | Volume:34 | Issue:4 (70) Page(s): 1-26

Download Full-Text

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Persian Verion

View:

2,649

Download:

Cites:

Information Journal Paper

Title

NEURAL NETWORK ENGINEERING USING LEARNING AUTOMATA: DETERMINATION OF DESIRED SIZE FOR THREE LAYERS FEED FORWARD NEURAL NETWORKS

Author(s)

MEYBODI M.R. | BEYGY H. | Issue Writer Certificate

Keywords

Not Registered.

Abstract

The goal of neural network engineering (NNE) is to study the advantages and disadvantages of neural networks and also providing methods to increase their performance. One of the problems in NNE is determination of optimal topology of neural networks for solving a given problem. There is no method to determine the optimal topology of multi-layer neural networks for a given problem. Usually, the designer selects a topology for neural networks and then trains it. The selected topology remains fixed during the training period. The performance of neural network depends on its size (number of hidden layers and hidden units). Determination of the optimal topology of neural network is an intractable problem. Therefore, most of algorithms for determination of the topology of neural network are approximate algorithms. These algorithms could be classified into five main groups: pruning algorithms, constructive algorithms, hybrid algorithms, evolutionary algorithms, and learning automata based algorithms. The only learning automata (LA) based algorithms, called survival algorithm, has been proposed by Beigy and Meybodi. This algorithm uses an object migrating learning automata and error back propagation (BP) algorithm and determines the number of hidden units of three layers neural networks, as training proceeds. In this paper, we propose three algorithms which are based on LA and BP. These algorithms determine a near optimal topology with low time complexity and high generalization capability for a given training set. These algorithms have two parts: determination of number of hidden units and determination of the number of hidden weights. One of the proposed algorithms uses the survival algorithm to determine the number of hidden units. A new algorithm based on LA is proposed to determine the number of hidden weights. This algorithm deletes weights with small effect, which leads to lower time complexity and higher generalization rate. Two other algorithms do not omit the hidden units explicitly; a hidden unit is omitted when all its input weights are deleted. Most of the reported algorithms in the literature for determination of topology of neural networks use hill-climbing method and may stuck at local minima. The proposed algorithms use global search method which results in increasing the probability of escaping from local minima. The proposed algorithms have been tested on several problems such as: recognition of Farsi and English digits. Simulation results show that the produced networks have good performance. The proposed algorithms are compared with Karnin pruning algorithm.

Cites

ADAPTIVE UNIFORM FRACTIONAL CHANNEL ALGORITHMS

References

No record.

Cite

APA: Copy

MEYBODI, M.R., & BEYGY, H.. (2001). NEURAL NETWORK ENGINEERING USING LEARNING AUTOMATA: DETERMINATION OF DESIRED SIZE FOR THREE LAYERS FEED FORWARD NEURAL NETWORKS. JOURNAL OF FACULTY OF ENGINEERING (UNIVERSITY OF TEHRAN), 34(4 (70)), 1-26. SID. https://sid.ir/paper/14284/en

Vancouver: Copy

MEYBODI M.R., BEYGY H.. NEURAL NETWORK ENGINEERING USING LEARNING AUTOMATA: DETERMINATION OF DESIRED SIZE FOR THREE LAYERS FEED FORWARD NEURAL NETWORKS. JOURNAL OF FACULTY OF ENGINEERING (UNIVERSITY OF TEHRAN)[Internet]. 2001;34(4 (70)):1-26. Available from: https://sid.ir/paper/14284/en

IEEE: Copy

M.R. MEYBODI, and H. BEYGY, “NEURAL NETWORK ENGINEERING USING LEARNING AUTOMATA: DETERMINATION OF DESIRED SIZE FOR THREE LAYERS FEED FORWARD NEURAL NETWORKS,” JOURNAL OF FACULTY OF ENGINEERING (UNIVERSITY OF TEHRAN), vol. 34, no. 4 (70), pp. 1–26, 2001, [Online]. Available: https://sid.ir/paper/14284/en

Related Journal Papers