Computational Learning Theory

Addressing three important problems.

  • defining learning problems
  • showing specific algorithms work
  • show these problems are fundamentally hard

The tools that used to analyse learning question also are the tools to analyse the Algorithm in Computing.

Three important thing to a learning algorithm:

$\rightarrow$ Time

$\rightarrow$ Space

$\rightarrow$ Sample (data sample) or generaliazation


Inductive learning

Inductive learning : Learning from sample

  1. Probability of successful training (it might not work)
  2. Number of examples to train on
  3. Complexity of hypothesis class
  4. Accuracy to which target concept is approximated
  5. Manner in which training examples presented (batch)
  6. Manner in which training examples selected

Select training Examples

It matters that how we select training examples when a learner is needing to learn.

Learner/Teachers

  1. Learners asks questions of teachers. given sample x, ask c(x)
  2. Teacher give examples to help learners, teacher chooses x, tells c(x)
  3. Fixed distribution, x chosen from $D$ by nature
  4. Evils asked questions

to be continue..

Published 27 July 2015
blog comments powered by Disqus