What is Machine learning?

Machine learning is a data analytics technique that teaches computers to do what comes naturally to humans and animals.

Machine learning algorithms use computational methods to “learn” information directly from data without relying on a predetermined equation as a model.

It is   the field of study that gives computers the capability to learn without being explicitly programmed.

Machine learning data is not random because it contains structure that can be used to predict outcomes, or gain knowledge in some way. Ex: patterns of Amazon purchases can be used to recommend items.

• It is more difficult to design algorithms for such tasks (compared to, say, sorting an array or calculating a payroll). Such algorithms need data. Ex: construct a spam filter, using a collection of email messages labelled as spam/not spam.

• Data mining is used for the application of ML methods to large databases.

 • Ex of ML applications: fraud detection, medical diagnosis, speech or face recognition. 

• ML is programming computers using data (past experience) to optimize a performance criterion.

 ML relies on

1) Statistics and making inferences from sample data.

2) Numerical algorithms (linear algebra, optimization): optimize criteria, manipulate models.

3) Computer science: data structures and programs that solve a ML problem efficiently.

  

Model

1) It is a compressed version of a database.

2) It extracts knowledge from it.

3) It does not have perfect performance but is a useful approximation to the data.