A NEW FAST PRE-TRAINING METHOD FOR TRAINING OF DEEP NEURAL NETWORK

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.

SEYYEDSALEHI SEYYEDE ZOHREH; SEYYED SALEHI SEYYED ALI

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

Journal Paper

Paper Information

Journal: SIGNAL AND DATA PROCESSING Year:2013 | Volume:- | Issue:1 (SERIAL 19) Page(s): 13-26

Download Full-Text

Persian Verion

View:

928

Download:

Cites:

Information Journal Paper

Title

A NEW FAST PRE-TRAINING METHOD FOR TRAINING OF DEEP NEURAL NETWORK

Author(s)

SEYYEDSALEHI SEYYEDE ZOHREH | SEYYED SALEHI SEYYED ALI | Issue Writer Certificate

Keywords

DEEP ARCHITECTUREQ2

LEARNING CONVERGENCEQ2

NEURAL NETWORKQ3

PRE-TRAININGQ2

Abstract

In this paper, we propose efficient method for PRE-TRAINING of deep bottleneck NEURAL NETWORK (DBNN). PRE-TRAINING is used for initial value of network weights; convergence of DBNN is difficult because of different local minimums. While with efficient initial value for network weights can avoided some local minimums. This method divides DBNN to multi single hidden layer and adjusts them, then weighs of these networks is used for initial value of DBNN weights and then train network. Proposed network is used for extraction of face component. This Method is implemented on Bosphorus database. Comparing results shows that new method has more convergence speed and generalization than random initial value. By means of this new training method and with same training error rate pixel reconstruction error is decreased 13.69% and recognition rate is increased 10%. Besides, it has been shown that this method bears higher efficiency and convergence speed in comparison with some of the previous PRE-TRAINING methods.

Cites

BIDIRECTIONAL LAYER-BY-LAYER PRE-TRAINING METHOD

References

No record.

Cite

APA: Copy

SEYYEDSALEHI, SEYYEDE ZOHREH, & SEYYED SALEHI, SEYYED ALI. (2013). A NEW FAST PRE-TRAINING METHOD FOR TRAINING OF DEEP NEURAL NETWORK. SIGNAL AND DATA PROCESSING, -(1 (SERIAL 19)), 13-26. SID. https://sid.ir/paper/160811/en

Vancouver: Copy

SEYYEDSALEHI SEYYEDE ZOHREH, SEYYED SALEHI SEYYED ALI. A NEW FAST PRE-TRAINING METHOD FOR TRAINING OF DEEP NEURAL NETWORK. SIGNAL AND DATA PROCESSING[Internet]. 2013;-(1 (SERIAL 19)):13-26. Available from: https://sid.ir/paper/160811/en

IEEE: Copy

SEYYEDE ZOHREH SEYYEDSALEHI, and SEYYED ALI SEYYED SALEHI, “A NEW FAST PRE-TRAINING METHOD FOR TRAINING OF DEEP NEURAL NETWORK,” SIGNAL AND DATA PROCESSING, vol. -, no. 1 (SERIAL 19), pp. 13–26, 2013, [Online]. Available: https://sid.ir/paper/160811/en

Related Journal Papers