Multilayer feedforward networks are universal approximators
Neural Networks
A Rosetta stone for connectionism
CNLS '89 Proceedings of the ninth annual international conference of the Center for Nonlinear Studies on Self-organizing, Collective, and Cooperative Phenomena in Natural and Artificial Computing Networks on Emergent computation
A comparison of Q-learning and classifier systems
SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence
Representational Difficulties with Classifier Systems
Proceedings of the 3rd International Conference on Genetic Algorithms
Mapping Neural Networks into Classifier Systems
Proceedings of the 3rd International Conference on Genetic Algorithms
Lamarckian Evolution, The Baldwin Effect and Function Optimization
PPSN III Proceedings of the International Conference on Evolutionary Computation. The Third Conference on Parallel Problem Solving from Nature: Parallel Problem Solving from Nature
Accuracy-based Neuro And Neuro-fuzzy Classifier Systems
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Is a learning classifier system a type of neural network?
Evolutionary Computation
Classifier fitness based on accuracy
Evolutionary Computation
Forming neural networks through efficient and adaptive coevolution
Evolutionary Computation
| Hi-index | 0.00 |
Learning Classifier Systems traditionally use a binary string rule representation with wildcards added to allow for generalizations over the problem encoding. We have presented a neural network-based representation to aid their use in complex problem domains. Here each rule's condition and action are represented by a small neural network, evolved through the actions of the genetic algorithm. In this paper we present results from the use of backpropagation in conjunction with the genetic algorithm within XCS. After describing the minor changes required to the standard production system functionality, performance is presented from using backpropagation in a number of ways within the system. Results from both continuous and discrete action tasks indicate that significant decreases in the time taken to reach optimal behaviour can be obtained from the incorporation of the local learning algorithm.