Basics of Machine Learning Series

Index

What is Machine Learning ?

Machine learning is the science of getting computers to learn, without explicitly being programmed. It has developed as a subset of the larger problem of building AI i.e. Artificially Intelligent systems.

Machine learning aims at developing new capabilities for computers wherein they can learn the objective intelligently without persistent human intervention, trying to mimic the way human brain learns.

Application of Machine Learning

• Database Mining: Large Datasets are abundantly available which cannot be easily interpretted by human analysis. A machine learning algorithm can give better insights into such datasets such as web search click through data. Similarly, machine learning can help convert medical records to structured data for running various analysis on it such as survival analysis, disease prediction etc. It can also be applied to biology, engineering etc.

• Non-programmable Applications: For example, one cannot write a program for autonomous driving cars, handwriting recognitions, most of the NLP problems such as word-sense disambiguation, computer vision etc.

• Self-customizing Programs: For example, the recommender systems from websites like amazon and netflix are machine learning algorithms because it would be impossible to write programs manually to serve each consumer personalized recommendations.

• Understanding human learning: Understanding how the human brain works will help in the building of AI.

Definations

• Field of study that gives the computers the ability to learn without being explicitly programmed.

Well-Posed Learning Problem: A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.

• Example: Playing chess
  • E = the experience of playing many games of chess
  • T = the task of playing chess
  • P = the probability that the program will win the next game

Types of Machine Learning Algorithms

• Supervised Learning
• Unsupervised Learning
• Others: Reinforcement Learning, Recommender Systems

REFERENCES:

Machine Learning: Coursera - Welcome
Machine Learning: Coursera - What is Machine Learning