Title :
An unpredictable-dynamics approach to neural intelligence
Author_Institution :
Jet Propulsion Lab., California Inst. of Technol., Pasadena, CA, USA
Abstract :
The theoretical basis for a dynamic neural network architecture that takes advantage of the notion of terminal chaos to process information in a way that is phenomenologically similar to brain activity is presented. The architecture exploits the phenomenology of nonlinear dynamic systems as an alternative to the traditional paradigm of finite-state machines. It is based on some effects of nonLipschitzian dynamics. The nonlinear phenomenon of terminal chaos and its relevance to brain activity are examined.<>
Keywords :
neural nets; nonlinear systems; brain activity; dynamic neural network architecture; finite-state machines; neural intelligence; nonLipschitzian dynamics; nonlinear dynamic systems; terminal chaos; unpredictable-dynamics approach; Adaptive systems; Artificial intelligence; Artificial neural networks; Biological system modeling; Biological systems; Brain; Chaos; Information processing; Neurons; Propulsion;
Journal_Title :
IEEE Expert