-=[ Docs ]=-

Evolutionary Algorithms for Neural Network Design and Training - (January 1995) Authors Jurgen Branke Language English Type public Url Summary Neural networks and evolutionary computation Pages 21 Parts Introduction Evolutionary Algorithms for Neural Network Training Evolutionary Algorithms to Determine the structure of a Neural Network Evolutionary Algorithms to Simultaneously Determine Weights and Structure of a Neural Network Further Work Competing Conventions Problem Conclusion

Genetic Algorithms and permutation problems: a comparison of recombination operators for neural net structure specification - (??) Authors Peter J.B. Hancock Language English Type public Url Summary finding neural network structures using genetic algorithms Pages 15 Parts Introduction Adressing the permutation problem Testing the operators Results Solving the permutation problem Competing Conventions Problem Conclusions

Genetic Encoding Strategies for Neural Networks - (??) Authors Philipp Kohn Language English Type public Url Summary Application of genetic algorithms to neural network optimization (GANN). Classification of the encoding strategies and analysis of current state of development. Pages 4 Parts The Problem of GANN Weight Encoding Architecture Encoding Tasks for GANN systems Fundamental Problems

Evolutionary Design Of Neural Architectures - A Preliminary Taxonomy and Guide to Literature - (January 1995) Authors Karthik Balakrishnan, Vasant Honavar Language English Type public Url Summary Taxonomy, literature, state of the art in evolutionary design of neural network architectures. Pages 49 Parts Introduction Evolutionary Design of Neural Architectures Towards a Taxonomy of EDNA Epilogue Bibliographie

Genetic Programming Discovers Effecient Learning Rules for the Hidden and Output Layers of Feedforward Neural Networks - (1999) Authors Amr Radi, Riccardo Poli Language English Type public Url Summary genetic programming, learning rules Pages 15 Parts 1 Introduction 2 Standard Backpropagation Algorithm and Recent Improvements 3 Previous Work on the Evolution of Neural Network Learning Rules 4 Evolution of Neural Network Learning Rules with GP 5 Experimental Results 6 Conclusions and Future Work