Introduction to Machine Learning

What is Machine Learning?

Machine learning is a branch of Artificial Intelligence, in which the computer based systems can be trained to automatically learn and improve themselves from their experiences. The machine learning based systems does not need to be explicitly programmed to perform a task.

Tom Mitchell provides a definition of machine learning as:

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.

So, essentially machine learning works by developing an algorithm or model (as popularly known in AI domain). This algorithm is provided with the data to train and test the algorithm.

A machine learning algorithm establishes relationship between input and output data. In some techniques, this relationship is established by feeding the sample input and corresponding output and in other techniques the algorithm itself establishes this relationship

Techniques of Machine Learning

The machine learning include following popular techniques among various others:

1. Supervised Learning

2. Unsupervised Learning

3. Reinforcement Learning

Supervised Learning

In supervised learning techniques, first the models are trained with labelled training data. It means model is trained with sample inputs having input data as well as the corresponding label. Once trained the technique helps to predict the output for the unseen input data.

Unsupervised Learning

In this class of machine learning techniques, models are trained with non-labelled training data. The model itself tries to extract the relationship among the input data items. The external labels are not provided to it.

Reinforcement Learning

This technique includes the set of problems which is based on interaction of an agent with its surrounding environment. The agent interacts with the environment using the feedbacks provided by environment for its various actions.

This section includes an initial introduction. In the next few sections, depth of each technique will be explored to develop the understanding.