Reflective controls for intelligent distributed objects
Proceedings of the 2001 ACM symposium on Applied computing
Stochastic Neural Computation II: Soft Competitive Learning
IEEE Transactions on Computers
A Heuristic Approach to the Inverse Differential Kinematics Problem
Journal of Intelligent and Robotic Systems
Classifier Ensembles with a Random Linear Oracle
IEEE Transactions on Knowledge and Data Engineering
Variations of the two-spiral task
Connection Science
Hi-index | 0.01 |
The Pandemonium system of reflective MINOS agents solves problems by automatic dynamic modularization of the input space. The agents contain feedforward neural networks which adapt using the backpropagation algorithm. We demonstrate the performance of Pandemonium on various categories of problems. These include learning continuous functions with discontinuities, separating two spirals, learning the parity function, and optical character recognition. It is shown how strongly the advantages gained from using a modularization technique depend on the nature of the problem. The superiority of the Pandemonium method over a single net on the first two test categories is contrasted with its limited advantages for the second two categories. In the first case the system converges quicker with modularization and is seen to lead to simpler solutions. For the second case the problem is not significantly simplified through flat decomposition of the input space, although convergence is still quicker