Decision theoretic generalizations of the PAC model for neural net and other learning applications

Information and Computation

Volumn 100, Issue 1, 1992, Pages 78-150

  Haussler, David ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0002192516     PISSN: 08905401     EISSN: 10902651     Source Type: Journal    
DOI: 10.1016/0890-5401(92)90010-D     Document Type: Article

References (97)

1. On the computational complexity of approximating distributions by probabilistic automata
2. Rates of growth for weighted empirical processes
3. Rates of growth and sample moduli for weighted empirical processes indexed by sets
4. Queries and concept learning
5. Learning from noisy examples
6. Fast probabilistic algorithms for Hamiltonian circuits and matchings
7. A result of Vapnik with Applications
8. Densité et dimension
9. Statistical properties of artificial neural networks
10. Minimum complexity density estimation
11. Pattern recognizing stochastic learning automata
12. What size net gives valid generalization?
13. Learnability by fixed distributions
14. Learnability and the Vapnik-Chervonenkis dimension
15. A Theory of Learning Classification Rules
16. Bayesian back propagation
17. Information-theoretic asymptotics of Bayes methods
18. Capacity problems for linear machines
19. Automatic learning, rule extraction and generalization
20. Automatic pattern recognition: A study of the probability of error
21. Central limit theorems for empirical measures
22. A course on empirical processes
23. Universal Donsker classes and metric entropy
24. Product units A computationally powerful and biologically plausible extension to backpropagation networks
25. A general lower bound on the number of examples needed for learning
26. Information dimension and the probabilistic structure of chaos
27. The dimension of chaotic attractors
28. A stochastic reinforcement algorithm for learning real-valued functions
29. Statistical theory of learning a rule
30. Quantifying inductive bias: AI learning algorithms and Valiant's learning framework
31. Learning conjunctive concepts in structural domains
32. Decision theoretic generalizations of the PAC learning model
33. Equivalence of models for polynomial learnability
34. Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension
35. Epsilon nets and simplex range queries
36. On the learnability of Boolean formulae
37. Efficient distribution-free learning of probabilistic concepts
38. ε-entropy and ε-capacity of sets in functional spaces
39. Optimal brain damage
40. The present position in Bayesian Statistics
41. Results on learnability and the Vapnik-Chervonenkis dimension
42. Learning quickly when irrelevant attributes abound: A new linearthreshold algorithm
43. Bayesian Methods for Adaptive Models
44. Fast Learning in networks of locally-tuned processing units
45. Learning over classes of distributions
46. Two new frameworks for learning
47. U-processes Rates of convergence
48. Maximum Likelihood Competitive Learning
49. Calculation of the learning curve of Bayes optimal classification algorithm for learning a perceptron with noise
50. Generalization performance of Bayes optimal classification algorithm for learning a perceptron
51. Empirical Processes: Theory and Applications
52. Stochastic complexity and modeling
53. On the density of families of sets
54. Learning k-DNF with noise in the attributes
55. Types of noise in data for concept learning
56. Learning from examples in large neural networks
57. Consistent inference of probabilities in layered networks: Predictions and generalizations
58. A theory of the learnable
59. Inductive principles of the search for empirical dependences (methods based on weak convergence of probability measures
60. Predicting the future A connectionist approach
61. Partition trees for triangle counting and other range search problems
62. Some special Vapnik-Chervonenkis classes
63. Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings
64. Learning in artificial neural networks A statistical perspective
65. A learning criterion for stochastic rules