Dynamic, genetic and chaotic programming: the sixth generation
Explains and applies five paradigms (rule-based computing, genetic programming/algorithms, natural adaptation, software of chaos) to dynamic processes such as robotics, natural languages, control, complex system design or optimization. Offers in-depth examination of the underlying principles and then concentrates on concrete examples, real-world problems and applications.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Dynamic Systems Control via Associative Reinforcement
Knowledge Acquisition for Dynamic System Control
Analysis of Recurrent Back Propagation and Its Application
10 other sections not shown
adaptive applied artificial attractor average back-propagation behavior best single individual best-of-generation individual binary bits Boolean functions chaos Chaotic Programming chapter chromosome circuit complex components computer program Conf configuration convergence corresponding crossover operation defined described dynamic equations error estimated evaluation evolution strategy example exemplar map fitness function fitness value genetic algorithm genetic operators genetic programming GP paradigm hidden units IEEE initial random input Internat inverse inverse kinematics iteration LISP machine Machine Learning manipulator method multiprocessor scheduling mutation optimal output parameters parent partitioning Perceptron performance player point pattern population possible prediction probability problem Proc prototypes randomly raw fitness recurrent neural network reinforcement learning reproduction robot S-expression sample schema search nodes search space selected self-organization sequence shown in Figure signal simulation solution solve stack filters standardized fitness step string structure supervised learning task terminal tion training sentences trajectories variables vector weights
Inventing Software: The Rise of "computer-related" Patents
Limited preview - 1998
All Book Search results »