Skip to content

Latest commit

 

History

History
29 lines (18 loc) · 749 Bytes

lecture1-overview.md

File metadata and controls

29 lines (18 loc) · 749 Bytes

Lecture 1 Overview

What is ML

Machine Learning/ Statistics/ Probability/ Computer Science/ Optimization

Examples:

  • Speech Recognition - Learning to recognize spoken words.
  • Robotics - Learning to drive an autonomous vehicle.
  • Games/ Reasoning - Learning to beat the masters at board games.
  • Computer Vision - Learning to recognize images.
  • Learning Theory - In what cases and how well can we learn?

Defining learning problems

Three components <T,P,E>:

  1. Task, T
  2. Performance measure, P
  3. Experience, E

Definition of learning:

A computer program learns if its performance at tasks in T, as measured by P, improves with experience E.

Problem formulation

The same task can be formulated in more than one way.