Pattern recognition in a neural network with chaos
Zheng‐Hua Tan, Mazhar Ali · Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics · 1998
Chaos is introduced into the Gardner model [J. Phys. A 21, 257 (1988); 22, 1969 (1989)] by reducing the number of connections among neurons. It is shown that patterns can be recognized in this chaotic model by means of chaos control focusing on the history of evolution of the states. Fixed points are not required for pattern recognition in this scheme.