The pandemonium system of reflective agents
- 1 January 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 7 (1) , 97-106
- https://doi.org/10.1109/72.478395
Abstract
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.Keywords
This publication has 11 references indexed in Scilit:
- Learning distributed representations of concepts using linear relational embeddingIEEE Transactions on Knowledge and Data Engineering, 2001
- Neural Networks and the Bias/Variance DilemmaNeural Computation, 1992
- Kolmogorov's theorem and multilayer neural networksNeural Networks, 1992
- Limitations of multi-layer perceptron networks - steps towards genetic neural networksParallel Computing, 1990
- Construction of a large-scale neural network: Simulation of handwritten Japanese character recognition on NCUBEConcurrency: Practice and Experience, 1990
- Neural network ensemblesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Theory of the backpropagation neural networkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- Learning representations by back-propagating errorsNature, 1986
- Pattern Recognition by MachineScientific American, 1960