Title :
Handwritten digits recognition system via OCON neural network by pruning selective update
Author :
Tsay, Shuh-Chuan ; Hong, Peir-Ren ; Chieu, Bin-Chang
Author_Institution :
Dept. of Electron. Eng., Nat. Taiwan Inst. of Technol., Taipei, Taiwan
fDate :
30 Aug-3 Sep 1992
Abstract :
Performs the handwritten digits recognition using the OCON (one-class-one-net) network and the PSU (pruning selective update) training algorithm. The main feature of the architecture of OCON network is that the entire network is composed of single output multi-layer perceptron and each of the subnets represents one class. The PSU training algorithm defined on the new cost function is designed to speed up the training procedure. It is shown that an OCON network with the new training algorithm outperforms the conventional back-propagation algorithm
Keywords :
character recognition; learning (artificial intelligence); neural nets; OCON neural network; cost function; handwritten digits recognition; output multi-layer perceptron; pruning selective update; training algorithm; Algorithm design and analysis; Clustering algorithms; Computer networks; Cost function; Handwriting recognition; Neural networks; Pattern classification; Shape; System testing; Writing;
Conference_Titel :
Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-8186-2915-0
DOI :
10.1109/ICPR.1992.201862
