Multitasking application of neural networks implementing metric methods of recognition

DOI10.1134/S000511791309004XMaRDI QIDQ386921zbMATH OpenOpenAlexFDO

Authors P. Sh. Geidarov

Publication date 11 December 2013

Published in Automation and Remote Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1134/s000511791309004x

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence (68T35)

Recommendations

• Neural network construction for recognition problems with standard information on the basis of a model of algorithms with piecewise linear surfaces and parameters
• Comparative analysis of the results of training a neural network with calculated weights and with random generation of the weights
• An approach to the solution of recognition problems using neural networks
• Applying neural networks to practical problems -- methodological considerations
• Metric-guided multi-task learning

Cites work

• scientific article; zbMATH DE number 877116 (Why is no real title available?)
• Stability of Hopfield neural networks

Cited in

(2)

• Comparative analysis of the results of training a neural network with calculated weights and with random generation of the weights
• The architecture of a neural network with a sequential division of images into pairs

This page was built for publication: Multitasking application of neural networks implementing metric methods of recognition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q386921)