Title :
Pattern recognition and learning in bistable CAM networks
Author :
Chinarov, Vladimir ; Dudziak, Martin ; Menzinger, Michael ; Kyrpach, Yuri
Author_Institution :
Dept. of Chem., Toronto Univ., Ont., Canada
Abstract :
The presented study concerns problems of learning, pattern recognition and computational abilities in an homogeneous network composed from coupled bistable units. New possibilities for pattern recognition may be realized due to the developed technique permitting reconstruction of a dynamical system using distributions of its attractors. In both cases the updating procedure for the coupling matrix uses the minimization of least-mean-square errors between the applied and desired patterns
Keywords :
content-addressable storage; learning (artificial intelligence); least mean squares methods; neural nets; pattern recognition; bistable CAM networks; computational abilities; coupled bistable units; coupling matrix; dynamical system; homogeneous network; least-mean-square errors; updating procedure; Biological system modeling; CADCAM; Chemistry; Computer aided manufacturing; Computer networks; Electronic mail; Intelligent networks; Oscillators; Pattern recognition; Potential well;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.832600
