For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A Constructive Compound Neural Networks. II Application to Artificial Life in a Competitive Environment
Jianjun YAN Naoyuki TOKUDA Juichi MIYAMICHI
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2000/04/25
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Artificial Intelligence, Cognitive Science
neural networks construction, artificial life, fuzzy logic, genetic algorithm, reinforcement learning,
Full Text: PDF>>
We have developed a new efficient neural network-based algorithm for Alife application in a competitive world whereby the effects of interactions among organisms are evaluated in a weak form by exploiting the position of nearest food elements into consideration but not the positions of the other competing organisms. Two online learning algorithms, an instructive ASL (adaptive supervised learning) and an evaluative feedback-oriented RL (reinforcement learning) algorithm developed have been tested in simulating Alife environments with various neural network algorithms. The constructive compound neural network algorithm FuzGa guided by the ASL learning algorithm has proved to be most efficient among the methods experimented including the classical constructive cascaded CasCor algorithm of , and the fixed non-constructive fuzzy neural networks. Adopting an adaptively selected best sequence of feedback action period Δα which we have found to be a decisive parameter in improving the network efficiency, the ASL-guided FuzGa had a performance of an averaged fitness value of 541.8 (standard deviation 48.8) as compared with 500(53.8) for ASL-guided CasCor and 489.2 (39.7) for RL-guided FuzGa. Our FuzGa algorithm has also outperformed the CasCor in time complexity by 31.1%. We have elucidated how the dimensionless parameter food availability FA representing the intensity of interactions among the organisms relates to a best sequence of the feedback action period Δα and an optimal number of hidden neurons for the given configuration of the networks. We confirm that the present solution successfully evaluates the effect of interactions at a larger FA, reducing to an isolated solution at a lower value of FA. The simulation is carried out by thread functions of Java by ensuring the randomness of individual activities.