Title :
Extending ETL for multi-class output
Author :
Chaudhari, Narendra S. ; Tiwari, Aruna
Author_Institution :
Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore
Abstract :
We present a method for extending the expand and truncate learning (ETL) technique for multi-class output. Kim and Park (1995) have given two hints for solving the same problem, but their hints may result in a large sized neural net. Here, we propose another method for the same problem, which is expected to result in a smaller neural net. Our method is based on yet other known technique introduced by Gray and Michel (1992), called the Boolean like training algorithm.
Keywords :
Boolean functions; learning (artificial intelligence); neural nets; Boolean algebra; Boolean like training algorithm; expand and truncate learning; multiclass output; neural net; Convergence; Hamming distance; Logic; Neurons;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1198979