0885-6125

Machine Learning (ML) - February 1994, issue 2 论文列表

本期论文列表
Guest Editorial

Hypothesis-Driven Constructive Induction in AQ17-HCI: A Method and Experiments

Concept Formation During Interactive Theory Revision

A Polynomial Approach to the Constructive Induction of Structural Knowledge

Flattening and Saturation: Two Representation Changes for Generalization

Explicit Representation of Concept Negation

Foreword

Foreword

Randomly Fallible Teachers: Learning Monotone DNF with an Incomplete Membership Oracle

Randomly fallible teachers: Learning monotone DNF with an incomplete membership oracle

Tracking Drifting Concepts By Minimizing Disagreements

Tracking drifting concepts by minimizing disagreements

Learning Probabilistic Read-once Formulas on Product Distributions

Learning probabilistic read-once formulas on product distributions

Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension

Bounds on the Sample Complexity of Bayesian Learning Using Information Theory and the VC Dimension

Approximation and estimation bounds for artificial neural networks

Approximation and Estimation Bounds for Artificial Neural Networks

Algorithms and lower bounds for on-line learning of geometrical concepts

Algorithms and Lower Bounds for On-Line Learning of Geometrical Concepts

The Power of Self-Directed Learning

The power of self-directed learning

TD(λ) converges with probability 1

TD(λ) Converges with Probability 1

Introduction to the Abstracts of the Invited Talks Presented at ML92 Conference in Aberdeen, 1–3 July 1992

Introduction to the abstracts of the invited talks presented at ML92 conference in Aberdeen, 1–3 July 1992

Machine learning and qualitative reasoning

Machine Learning and Qualitative Reasoning

Children, Adults, and Machines as Discovery Systems

Children, adults, and machines as discovery systems

Combining Symbolic and Neural Learning

Combining symbolic and neural learning

Statistical Methods for Analyzing Speedup Learning Experiments

Statistical methods for analyzing speedup learning experiments