Machine learning at its most basic is the practice of using algorithms to parse data, learn from it, and then make a determination or prediction about something in the world. It is based on algorithms that can learn from data without relying on rules-based programming. In particular, it can deal with

• a large amount of data;
• data with no pre-determined underlying structure;
• data with many dimensions;
• data with a high degree of non-linearity.

There are three classes of techniques.

Supervised Learning

Supervised learning is where you have input variables (x, or features) and an output variable (Y, or target), and you use an algorithm to learn the mapping function from the input to the output (prediction rule).

Y = f(X)

The intent is to train the function so such an extent that whenever we have any new input data (x) you can easily predict the output variables (Y) for that given set of input data.

Supervised learning can be divided into two categories of problems: regression problems and classification problems.

Continuous target (Y) variable - regression problem. Regression means to predict the output value using training data.

Categorical or ordinal target (Y) variable - classification problem. Classification means to group the output into a class.

Unsupervised Learning

It draws inferences from datasets consisting of input data without labeled responses. It is used to "discover" the underlying structure of the data.

Problem: too much data!
Solution: Reduce it.

Dimension reduction: reduce number of dimensions. It looks a lot like compression. This is about trying to reduce the complexity of the data while keeping as much of the relevant structure as possible.

Clustering: reduce number of examples. It allows you to automatically split the dataset into groups according to similarity.

Deep Learning and Reinforcement Learning

This area of ML includes deep learning, in which a computer learns from interacting with itself. Sophisticated algorithms address such highly complex tasks as image classification, face recognition, speech recognition and natural language processing, and reinforcement learning.