| 
  • If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • Stop wasting time looking for files and revisions. Connect your Gmail, DriveDropbox, and Slack accounts and in less than 2 minutes, Dokkio will automatically organize all your file attachments. Learn more and claim your free account.

View
 

Theory

Page history last edited by olivier 14 years, 2 months ago

Foundations of Learning Theory

 

Machine Learning relates to many different domains: data analysis, data processing, information retrieval, statistics, knowledge discovery, reasoning under uncertainty, game theory, decision theory...

 

But the main distinguishing feature of the learning problem is that it requires a form of reasoning which is non-deductive: it requires induction, transduction, abduction or generalization.

 

As a result, the learning problem has its roots in the following theories

 

 

  • Formalizing decision-making and interactions
    • Decision Theory W
    • Auction Theory W
    • Rational Choice Theory, Public choice theory, Social choice theory, General equilibrium theory W...
    • Portfolio Theory W, Sharpe ratio W
    • Theory of Risk Aversion W, Utility W
    • Game Theory W, Mechanism Design W, What is Game Theory?, by D. K. Levine.
    • Finance, Gambling Theory W, Arbitrage W, Prediction Markets W, Efficient market theory W, Value-at-Risk W, Hedge W
    • Interpretation of Probability W

 

  • Formalizing information and regularity
    • Information Theory W
    • Algorithmic Information Theory W
    • Compression W, Universal compression
    • Randomness W

 

  • Formalizing Inference
    • Logic Inference
    • Inductive Inference W
    • Statistical Inference
    • Estimation Theory

 

  • Tools
    • Probability Theory
    • Optimization Theory
    • Algorithms, Computation Theory
    • Functional Analysis
    • Approximation Theory

Comments (0)

You don't have permission to comment on this page.