On the capabilities of multilayer perceptrons

Journal of Complexity

Volumn 4, Issue 3, 1988, Pages 193-215

  Baum, Eric B ^a  

^a CALIFORNIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0001632845     PISSN: 0885064X     EISSN: 10902708     Source Type: Journal    
DOI: 10.1016/0885-064X(88)90020-9     Document Type: Article

References (37)

1. Number of synapses per neuron
2. Random problems
3. Optical neural computers
4. Information capacity of the Hopfield model
5. A learning algorithm for Boltzmann machines
6. Generalizing back propagation to computation
7. Classifying learnable geometric concepts with the Vapnik-Chernovenkis dimension
8. An outline of a mathematical theory of PAPA
9. Information theoretic computational complexity
10. Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition
11. Further experiments with PAPA
12. Learned classification of sonar targets using a massively parallel network
13. Learning and relearning in Boltzmann machines
14. Neural networks and physical systems with emergent collective computational abilities
15. Three approaches for defining the concept of information quantity
16. A learning procedure for asymmetric threshold networks
17. A logical calculus of the ideas immanent in neural nets
18. The capacity of the Hopfield associative memory
19. Some mathematical models of learning
20. Learning Logic
21. Learning internal representations by error propagation
22. Some studies in machine learning using the game of checkers
23. Some studies in machine learning using the game of checkers Part II
24. NET Talk: A parallel network that learns to read aloud
25. An empirical test of new forecasting methods derived from a theory of intelligence: The prediction of conflict in Latin America