Title :
A technique for defining the architecture and weights of a neural image classifier
Author :
Re, R. ; Roli, F. ; Serpico, S.B. ; Vernazza, G.
Author_Institution :
Dept. of Biophys. & Electron. Eng., Genoa Univ., Italy
Abstract :
An approach to setting the architecture and the initial weights of an artificial neural network for solving classification problems is presented. A nonneural phase finds an approximate solution to the classification problems by constraining the shape of classification regions. After an appropriate mapping into a neural net, neural training is applied to refine the solution. Results on an image recognition application are presented
Keywords :
image recognition; neural nets; artificial neural network; classification problems; image recognition; initial weights; mapping; neural image classifier; neural training; Artificial neural networks; Computer architecture; Fault tolerance; Image processing; Image recognition; Image restoration; Parallel processing; Shape; Sonar; Speech recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0532-9
DOI :
10.1109/ICASSP.1992.226035
