NEW LEARNING AUTOMATA BASED ALGORITHMS FOR DETERMINING THE NUMBER OF INPUT WEIGHTS OF HIDDEN LAYERS IN A MULTI LAYER 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.

MASHOUFI B.; MEYBODI M.R.; MOTAMEDI S.A.; MENHAJ M.B.

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

Journal Paper

Paper Information

Journal: AMIRKABIR Year:2004 | Volume:15 | Issue:58-A (TOPICS IN: ELECTRICAL ENGINEERING) Page(s): 286-319

Download Full-Text

Persian Verion

View:

584

Download:

Cites:

Information Journal Paper

Title

NEW LEARNING AUTOMATA BASED ALGORITHMS FOR DETERMINING THE NUMBER OF INPUT WEIGHTS OF HIDDEN LAYERS IN A MULTI LAYER NEURAL NETWORKS

Author(s)

MASHOUFI B. | MEYBODI M.R. | MOTAMEDI S.A. | MENHAJ M.B. | Issue Writer Certificate

Keywords

NEURAL NETWORKS ENGINEERINGQ4

MULTI LAYER NEURAL NETWORKSQ4

NEURAL NETWORKS TOPOLOGYQ4

BACK PROPAGATION ALGORITHMQ3

LEARNING AUTOMATAQ4

Abstract

Back propagation algorithm performs gradient descent only in the weight space of a network with fixed topology. The Number of layers, Neurons and network weights have important influence on network performance. So algorithms that can find appropriate network architecture automatically are thus highly desirable. Researchers have proposed different algorithms for determining optimum size of neural networks. Meybod and Beigy introduced the first LEARNING AUTOMATA based algorithms, called WSA algorithm. This algorithm by turning off the unimportant weights, not only reduces network complexity but also increases network generalization ability, at the beginning, all weights of the network are on and contribute to learning. The on weights, whose absolute values are less than a threshold value, are penalized and those whose absolute value is larger than another threshold value, are rewarded. The on weights, whose absolute values lie between these two threshold values, neither rewarded, nor penalized. By choosing optimum values for these values we can obtain, networks with minimum number of weights which can learn training patterns with acceptable error and generalization ability. In this paper we introduce a new LEARNING AUTOMATA based algorithm, called A WSA for adaptation of parameters of WSA algorithm. Also, a new algorithm called MWSA is introduced to determine important weights in the MULTI LAYER NEURAL NETWORKS. These algorithms are applied to number of problems such as recognition of English number. Persian printed numbers recognition, second order discrete time nonlinear function approximation and Persian phoneme recognition. The results obtained show that the proposed algorithms have better performance than, other existing algorithms.

Cites

No record.

References

No record.

Cite

APA: Copy

MASHOUFI, B., MEYBODI, M.R., MOTAMEDI, S.A., & MENHAJ, M.B.. (2004). NEW LEARNING AUTOMATA BASED ALGORITHMS FOR DETERMINING THE NUMBER OF INPUT WEIGHTS OF HIDDEN LAYERS IN A MULTI LAYER NEURAL NETWORKS. AMIRKABIR, 15(58-A (TOPICS IN: ELECTRICAL ENGINEERING)), 286-319. SID. https://sid.ir/paper/693/en

Vancouver: Copy

MASHOUFI B., MEYBODI M.R., MOTAMEDI S.A., MENHAJ M.B.. NEW LEARNING AUTOMATA BASED ALGORITHMS FOR DETERMINING THE NUMBER OF INPUT WEIGHTS OF HIDDEN LAYERS IN A MULTI LAYER NEURAL NETWORKS. AMIRKABIR[Internet]. 2004;15(58-A (TOPICS IN: ELECTRICAL ENGINEERING)):286-319. Available from: https://sid.ir/paper/693/en

IEEE: Copy

B. MASHOUFI, M.R. MEYBODI, S.A. MOTAMEDI, and M.B. MENHAJ, “NEW LEARNING AUTOMATA BASED ALGORITHMS FOR DETERMINING THE NUMBER OF INPUT WEIGHTS OF HIDDEN LAYERS IN A MULTI LAYER NEURAL NETWORKS,” AMIRKABIR, vol. 15, no. 58-A (TOPICS IN: ELECTRICAL ENGINEERING), pp. 286–319, 2004, [Online]. Available: https://sid.ir/paper/693/en

Related Journal Papers