Machine learning is being used by people in various ways knowingly or unknowingly. Each time when we Google or Bing search we get the best results because they have used machine learning to rank page. The world biggest search engine giant Google offers recommendation and suggestion based on the previous user searches. In 2012, Google introduced Knowledge Graph -an algorithm used to decipher the semantic content of a search query. Facebook uses a face recognition algorithm to detect and recognize your friends in the photos that you uploaded. Gmail uses machine learning to filter spam email.

Arthur Samuel described “the field of study that gives computers the ability to learn without being explicitly programmed.” This is an older, informal definition.

Other great applications of machine learning are image recognition like handwritten number recognition, speech recognition like Siri and Cortana, medical applications. Machine learning is the science of getting computers to learn, without being explicitly programmed. Many scientists believe the best way to get incredible results is by using the learning algorithm i.e. Neural Networks which mimic how the human brain works.

Tom Mitchell provides a more modern definition: “A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.”

Example: playing checkers.

E = the experience of playing many games of checkers

T = the task of playing checkers.

P = the probability that the program will win the next game.

In general, any machine learning problem can be assigned to one of two broad classifications:

• Supervised Learning
• Unsupervised learning

Other learning algorithms are reinforcement learning, recommender system etc. In supervised learning, we teach a computer how to do learning whereas in unsupervised learning computer learn by itself.

Reference:

Andrew Ng Machine learning course from coursera