Extending and Unifying Formal Models for Machine Learning

Abstract

There has been a great deal of work on statistical pattern recognition, non-parametric estimation, and formal models of machine learning. Recent and classical work in these areas have provided fundamental results on the amount of data needed for classification, estimation, and prediction in a variety of non-parametric settings. The applicability of these paradigms is often limited by the assumptions on the data gathering mechanisms and the performance criteria. Our work has had two primary goals. The first is to investigate extensions and new models which give results useful in broader applications. The second goal is to apply these learning results to other areas such as signal/image processing, geometric reconstruction, and system identification. We have studied a variety of problems and have been able to relax assumptions required on the observed data as well as on the success criteria while still obtaining positive results. Our results have provided new insights into classical work and have also suggested a number of directions for further work.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 30, 1997
Accession Number
ADA328730

Entities

People

  • Sanjeev R. Kulkarni

Organizations

  • Princeton University

Tags

Communities of Interest

  • Autonomy
  • Human Systems
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Classification
  • Consistency
  • Data Science
  • Electrical Engineering
  • Hybrid Systems
  • Identification
  • Image Processing
  • Information Processing
  • Information Science
  • Information Theory
  • Learning
  • Machine Learning
  • Pattern Recognition
  • Probability
  • Signal Processing
  • Statistics

Fields of Study

  • Computer science

Readers

  • Statistical inference.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms