Dynamic node architecture learning: An information theoretic approach

Neural Networks

Volumn 7, Issue 1, 1994, Pages 129-140

  Bartlett, Eric B ^a  

^a IOWA STATE UNIVERSITY   (United States)

Author keywords

Connectionism; Dynamic node allocation; Network architectures; Neural network computing; Optimization; Supervised learning

Indexed keywords

NEURAL NETWORKS; OPTIMIZATION;

CONNECTIONISM; DYNAMIC LOAD ALLOCATION; SUPERVISED LEARNING;

LEARNING SYSTEMS;

EID: 0028208150     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(94)90061-2     Document Type: Article

References (48)

1. Dynamic node creation in backpropagation networks
2. Nuclear power plant status diagnostics using simulated condensation: an auto-adaptive computer learning technique
3. Chaotic time series prediction using artificial neural networks
4. Analysis of chaotic population dynamics using artificial neural networks
5. A dynamic node architecture scheme for backpropagation neural networks
6. Nuclear power plant status diagnostics using artificial neural networks
7. A self-optimizing stochastic dynamic node learning algorithm for layered neural networks
8. Nuclear power plant status diagnostics using an artificial neural network
9. A self-optimizing stochastic dynamic node learning algorithm for layered neural networks
10. General asymmetric neural networks and structure design by genetic algorithms
11. The Stone-Weierstrass theorem and its application to neural networks
12. Learning coefficient dependence on training set size
13. A connectionist learning algorithm with provable generalization and scaling bounds
14. Kolmogorov's mapping neural network existence theorem
15. Theory of the backpropagation neural network
16. Back-propagation algorithm which varies the number of hidden units
17. A structural learning algorithm with forgetting of link weights
18. A simple procedure for pruning back propagation trained neural networks
19. Optimization by simulated annealing
20. On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition
21. Improving generalization in back-propagation networks with distributed bottlenecks
22. From Stein's unbiased risk estimates to the method of generalized cross validation
23. An introduction to computing with neural nets
24. Back propagation error surfaces can have a local minima
25. Institute for Cognitive Science, University of California, San Diego
26. The golden age of theoretical ecology: 1932–1940: A collection of works by V. Volterra, V. A. Kostitzin, A. J. Lotka, and A. N. Kolmogoroff
27. Neural net pruning why and how
28. Asymptotics for and against cross-validation
29. Consistent inference of probabilities in layered networks: Predictions and generalization
30. Application of neural networks for sensor validation and plant monitoring
31. Adaptive neural architectures through growth control
32. Generalization by weight elimination applied to currency exchange rate prediction
33. Backpropagation and neural control: A review and prospectus
34. 30 years of adaptive neural networks: Perception, madaline, and backpropagation
35. A mathematical theory of generalization: Part 1 and 2
36. Stacked generalization
37. A comparison of connection pruning algorithms with backpropagation