Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications
Explore this paper's citation graph
Summary
Theorems on the uniform convergence of empirical loss estimates to true expected loss rates for certain hypothesis spaces H are given, and it is shown how this implies learnability with bounded sample size, disregarding computational complexity.
- Type
- article
- Published
- 1992-09-01
- Cited by
- 1,146
- References
- 92
- OpenAlex
- https://openalex.org/W2084544490
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:14921581
Keywords
Computer science, Net (polyhedron), Artificial neural network, Artificial intelligence, Machine learning
References
- Learning from examples in large neural networks.
- Large Automatic Learning, Rule Extraction, and Generalization
- Decision Theoretic Generalizations of the PAC Learning Model
- Some results on learning
- Extensions of a Theory of Networks for Approximation and Learning
- Empirical Processes: Theory and Applications
- The 1988 Wald Memorial Lectures: The Present Position in Bayesian Statistics
- Computer Systems That Learn
- Learning Automata: An Introduction
- On Uniform Convergence for Dependent Processes
- Consistent inference of probabilities in layered networks: predictions and generalizations
- Stochastic Complexity and Modeling
- Learning k-DNF with noise in the attributes
- On the Density of Families of Sets
- Statistical Decision Theory and Bayesian Analysis, Second Edition
- Learnability by fixed distributions
- Quantifying Inductive Bias: AI Learning Algorithms and Valiant's Learning Framework
- Predicting the Future: a Connectionist Approach
- Results on learnability and the Vapnik-Chervonenkis dimension
- ON CONVERGENCE OF STOCHASTIC PROCESSES
Cited by
- A Review of Some Extensions to the PAC Learning Model
- Foundations of Machine Learning
- A New Metric-Based Approach to Model Selection
- Randomized neural networks for learning stochastic dependences
- Perceptron Learning with Discrete Weights
- VC-Dimension Analysis of Object Recognition Tasks
- Learning Coverage Functions
- Geometric Concept Learning and Related Topics
- The Informational Complexity of Learning
- Some Topics in Neural Networks and Control
- Learning Halfspaces Under Log-Concave Densities: Polynomial Approximations and Moment Matching
- Approximation Algorithms and New Models for Clustering and Learning
- Liberal or Conservative: Evaluation and Classification with Distribution as Ground Truth.
- Robustness of Evolvability
- Penalized least squares, model selection, convex hull classes and neural nets
- VC dimension of neural networks
- On the sample complexity of reinforcement learning.
- Consistency versus Realizable H-Consistency for Multiclass Classification
- Efficient learning from faulty data
- Quantum Machine Learning: What Quantum Computing Means to Data Mining
Related papers
- Physician-Friendly Machine Learning: A Case Study with Cardiovascular Disease Risk Prediction
- Breakdown of Machine Learning Algorithms
- Application of Machine Learning in Animal Disease Analysis and Prediction
- Artificial Intelligence, Machine Learning, and Medicine: A Little Background Goes a Long Way Toward Understanding.
- A Comprehensive Review of Various Machine Learning Techniques
- Machine Learning and Deep Learning for Maize Leaf Disease Classification: A Review
- Machine Learning and Deep Learning Applications in Multiple Myeloma Diagnosis, Prognosis, and Treatment Selection
- An Optimal Solution to the Overfitting and Underfitting Problem of Healthcare Machine Learning Models