Title :
Training algorithms for GSNf neural networks
Author :
de Carvalho, A. ; Bisset, D. ; Fairhurst, M.
Author_Institution :
Dept. of Comput. Sci. & Stat., Sao Paulo Univ., Brazil
Abstract :
This paper presents and analyses distinct learning strategies which have been used by GSNf architectures. Sharing the common feature of being one-shot learning, these strategies achieve different performances as key parameters are changed. These algorithms are evaluated against each other by taking into account the training time, saturation rates, learning conflict rates and recognition performance
Keywords :
feedforward neural nets; learning (artificial intelligence); neural net architecture; pattern recognition; GSN neural networks; goal seeking neurons; learning algorithm; learning conflict rates; multilayer neural nets; neural net architectures; pattern recognition; saturation rates; training time; Character recognition; Machine learning; Neural networks; Neurons; Postal services; Velocity measurement;
Conference_Titel :
Cybernetic Vision, 1996. Proceedings., Second Workshop on
Conference_Location :
Sao Carlos
Print_ISBN :
0-8186-8058-X
DOI :
10.1109/CYBVIS.1996.629443
