(28) * << * >> * Russian * English * Content * All Issues
The article considers an algorithm for training a multilayer perceptron using a uniform test. It investigates the possibility to improve recognition characteristics by adjusting the criterion parameters using additional information about the achievable recognition quality obtained in the training process. An example of the algorithm application to the task of recognition of Arabic numerals is provided.
neural network, multilayer perceptron, Arabic numerals.
Fursov VA, Shustov VA. Optimization of recognition quality by selection of tolerances during neural network training. Computer Optics 2005; 28: 105-107.
© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: firstname.lastname@example.org ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20