What is Machine Learning?

Machine Learning is an application of Artificial Intelligence and a field of computer science which provides computer systems ability to learn without explicitly programmed. These systems improve from experience.

In simple terms, we write a computer program which uses the data to learn, grow and develop automatically.

Machine learning is used in Self-driving cars, online fraud detection, recommendation engines like Amazon which shows you items related to your recent searches, Netflix which show movies you might like and many more applications.

Machine learning algorithms takes certain type of data set and find pattern hidden in that data set to answer more questions. Every right and wrong answers are added back to its memory which makes the system more smarter.

Machine Learning methods

Supervised Learning

In supervised learning we have input variables and output variables and use these pairs of input-output objects (known as labeled data) to train the machine. The machine learn the mapping function from these labeled data and with every new labeled data the machine approximate the mapping function which will be used to make predictions. In simple terms, we can say that with some examples we teach our machine and make it capable of predicting.
Y = f(x), where x is input variable and Y is output variable.

Unsupervised Learning

In unsupervised learning we have input variables but no output variables. There is no correct answer as it is in supervised learning. So the algorithm has to discover some hidden patterns from the data set on its own. No one is there to teach the machine.

Unsupervised learning can be further categorized as:
1) Clustering: It is the assignment of a set of observations into subsets (known as clusters) such that observation in the same cluster are similar in some sense.
2) Association: It is a method of discovering interesting relations between variables in large databases.

Leave a Reply

Your email address will not be published. Required fields are marked *