Abstract | ||
---|---|---|
In this paper we introduce a self-organizing neural network that is capable of recognition of temporal signals. Conventional self-organizing neural networks like recurrent variant of Self-Organizing Map provide clustering of input sequences in space and time but the identification of the sequence itself requires supervised recognition process, when such network is used. In our network called TICALM the recognition is expressed by speed of convergence of the network while processing either learned or an unknown signal. TICALM network capabilities are shown on an experiment with handwriting recognition. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11840817_43 | ICANN (1) |
Keywords | Field | DocType |
conventional self-organizing neural network,temporal signal,ticalm network capability,recurrent variant,self-organizing neural network,handwriting recognition,signal recognition,input sequence,self-organizing map,unknown signal,supervised recognition process,self organization,neural network | Neocognitron,Pattern recognition,Computer science,Recurrent neural network,Handwriting recognition,Probabilistic neural network,Time delay neural network,Artificial intelligence,Cluster analysis,Artificial neural network,Machine learning,Neural gas | Conference |
Volume | ISSN | ISBN |
4131 | 0302-9743 | 3-540-38625-4 |
Citations | PageRank | References |
0 | 0.34 | 9 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jan Koutník | 1 | 552 | 36.31 |
Miroslav Šnorek | 2 | 49 | 6.41 |