Terminal Attractor Research Articles

Cerebral rhythms and temporal coherence

Some studies of scalp-conducted human EEG show a positive correlation between the temporal coherence of prestimulus activity in the theta, alpha, and beta passbands, on the one hand, and both target probability and subjective self-report about good performance, on the other. There remains an important ambiguity in these data: Are these changes in temporal coherence merely a reflection of changes in subjective relaxation, or do they index the timing of neural network convergences to terminal attractors? Other studies of human EEG during temporal conditioning paradigms suggest that the second alternative can be rigorously tested.

Neutral learning of constrained nonlinear transformations

Two issues that are fundamental to developing autonomous intelligent robots, namely rudimentary learning capability and dexterous manipulation, are examined. A powerful neural learning formalism is introduced for addressing a large class of nonlinear mapping problems, including redundant manipulator inverse kinematics, commonly encountered during the design of real-time adaptive control mechanisms. Artificial neural networks with terminal attractor dynamics are used. The rapid network convergence resulting from the infinite local stability of these attractors allows the development of fast neural learning algorithms. Approaches to manipulator inverse kinematics are reviewed, the neurodynamics model is discussed, and the neural learning algorithm is presented. >

Terminal attractors in neural networks

A new type of attractor—terminal attractors—for content-addressable memory, associative memory, and pattern recognition in artificial neural networks operating in continuous time is introduced. The idea of a terminal attractor is based upon a violation of the Lipschitz condition at a fixed point. As a result, the fixed point becomes a singular solution which envelopes the family of regular solutions, while each regular solution approaches such an attractor in finite time. It will be shown that terminal attractors can be incorporated into neural networks such that any desired set of these attractors with prescribed basins is provided by an appropriate selection of the synaptic weights. The applications of terminal attractors for content-addressable and associative memories, pattern recognition, self-organization, and for dynamical training are illustrated.

Terminal attractors for addressable memory in neural networks

A new type of attractors—terminal attractors—for an addressable memory in neural networks operating in continuous time is introduced. These attractors represent singular solutions of the dynamical system. They intersect (or envelope) the families of regular solutions while each regular solution approaches the terminal attractor in a finite time period. It is shown that terminal attractors can be incorporated into neural networks such that any desired set of these attractors with prescribed basins is provided by an appropriate selection of the weight matrix.

Terminal attractors in neural networks: [formula omitted]. Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Drive, Pasadena, California 91109

Neural networks made to learn faster. Report presents theoretical study of terminal attractors in neural networks. Includes systematic analysis of applications to activation dynamics of neural networks.