A review of evolutionary artificial neural networks

International Journal of Intelligent Systems

Volumn 8, Issue 4, 1993, Pages 539-567

  Yao, Xin ^a  

^a CSIRO   (Australia)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE SYSTEMS; ALGORITHMS; ARTIFICIAL INTELLIGENCE; DATA PROCESSING; INTERACTIVE COMPUTER SYSTEMS; LEARNING SYSTEMS; RESEARCH;

EVOLUTIONARY ARTIFICIAL NEURAL NETWORKS (EANNS); GENETIC ALGORITHMS;

NEURAL NETWORKS;

EID: 0027574256     PISSN: 08848173     EISSN: 1098111X     Source Type: Journal    
DOI: 10.1002/int.4550080406     Document Type: Article

References (98)

1. Evolution of connectionist networks
2. Learning internal representations by error propagation
3. Optimization by simulated annealing
4. Simulated annealing with extended neighbourhood
5. The upstart algorithm: A method for constructing and training feed‐forward neural networks,”
6. Skeletonization: A technique for trimming the fat from a network via relevance assessment,”
7. Creating artificial neural networks that generalize,”
8. Back‐propagation algorithm which varies the number of hidden units,”
9. Optimal brain damage
10. Parallel networks that learn to pronounce English text
11. A time‐delay neural network architecture for isolated word recognition
12. Learned classification of sonar target using a massively‐parallel network
13. Connectionist learning procedures
14. Optimizing neural networks using faster, more accurate genetic search
15. Evolving neural networks
16. Genetic algorithms and neural networks: Optimizing connections and connectivity
17. Parallel algorithms for learning in neural networks with evolution strategy
18. A quantized back propagation learning rule and its application to optical neural networks
19. Weight quantization in Boltzmann machines
20. Learning with limited numerical precision using the cascade‐correlation algorithm
21. Simulation of genetic populations with biochemical properties,” (Doctoral Dissertation, University of Michigan)
22. Classifier system and the Animate problem
23. Nonconvex optimization by fast simulated annealing
24. Designing neural networks using genetic algorithms with graph generation system
25. Using genetic search to exploit the emergent behavior of neural networks
26. Perceptron redux: Emergence of structure,”
27. Minimum class entropy: A maximum information approach to layered networks
28. An information criterion for optimal neural network selection
29. Occam's razor
30. Modeling by shortest data description,”
31. Scaling, Machine learning, and genetic neural nets,”
32. Fractally configured neural networks
33. Units of transcription and translation: Sequence components of heterogeneous nuclear RNA and messager RNA,”
34. Genetic synthesis of neural network architecture
35. Increased rates of convergence through learning rate adaptation
36. Evolving a learning algorithm for the binary perceptron
37. Different voltage‐dependent thresholds for inducing long‐term depression and long‐term potentiation in slices of rat visual cortex
38. When learning guides evolution
39. How learning can guide evolution
40. Evolution and learning in neural networks: the number and distribution of learning trials affect the rate of evolution
41. Adaptive switching circuits
42. Econets: Neural networks that learn in an environment
43. Evolution of connectionist networks