A neuro-hierarchial multilayer network in the translation of the American sign language

Author

Abdallah, Moussa

Author_Institution

Dept. of Electron. Eng., Princess Sumaya Univ., Amman, Jordan

fYear

1998

fDate

24-26 Apr 1998

Firstpage

224

Lastpage

227

Abstract

A neuro hierarchial approach based on an adaptive back-propagation algorithm is proposed. In a separate preprocessing step, the input and the output vector are generated using the encoded-sequence representation. The algorithm is applied to translate the American sign language from spoken words. Experimental results indicate that this approach results in fast convergence, stable learning and a relatively small network size when compared to traditional methods

Keywords

adaptive signal processing; backpropagation; biocommunications; language translation; multilayer perceptrons; pattern classification; speech recognition; American sign language; adaptive back-propagation algorithm; convergence; encoded-sequence representation; input vector; network size; neuro-hierarchial approach; neuro-hierarchial multilayer network; output vector; preprocessing step; spoken words; stable learning; translation; Computational efficiency; Computer architecture; Computer networks; Convergence; Data preprocessing; Error correction; Handicapped aids; Intelligent networks; Nonhomogeneous media; Object recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Southeastcon '98. Proceedings. IEEE

Conference_Location

Orlando, FL

Print_ISBN

0-7803-4391-3

Type

conf

DOI

10.1109/SECON.1998.673334

Filename

673334