Title :
Application of knowledge-based cascade-correlation to vowel recognition
Author :
Rivest, François ; Shultz, Thomas R.
Author_Institution :
Sch. of Comput. Sci., McGill Univ., Montreal, Que., Canada
fDate :
6/24/1905 12:00:00 AM
Abstract :
Neural network algorithms are usually limited in their ability to use prior knowledge automatically. A recent algorithm, a knowledge-based cascade-correlation (KBCC), extends the cascade-correlation by evaluating and recruiting previously learned networks in its architecture. In this paper, we describe KBCC and illustrate its performance on the problem of recognizing vowels
Keywords :
correlation methods; knowledge based systems; learning (artificial intelligence); neural nets; speech recognition; cascade-correlation; knowledge-based systems; learning; neural network; speech recognition; vowel recognition; Application software; Artificial neural networks; Computer science; Humans; Impedance matching; Neural networks; Psychology; Recruitment; Silver; Speech recognition;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005441
