Deep learning

Neural network explained 


Finds patterns (and develops predictive models) using both, input data and output data.

Supervised Learning:

Finds patterns (and develops predictive models) using both, input data and output data.

All Supervised Learning techniques area form of either Classification or Regression.


Classification is used for predicting discrete responses.

For example:

Whether India will WIN or LOSE a Cricket match?Whether an email is SPAM or GENUINE?

WIN, LOSE, SPAM, GENUINE are the predefined classes. And output has to fall among these depending on the input.


Regression is used for predicting continuous responses.

For example:

Trend in stock market prices, Weather forecast, etc.

Unsupervised Learning:

Finds patterns based only on input data. This technique is useful when you’re not quite sure what to look for. Often used for exploratory Analysis of raw data.

Most Unsupervised Learning techniques are a form of Cluster Analysis.

Cluster Analysis:

In Cluster Analysis, you group data items that have some measure of similarity based on characteristic values.

At the end what you will have is a set of different groups (Let’s assume A — Z such groups). A Data Item(d1) in one group(A) is very much similar to other Data Items(d2 — dx) in the same group(A), but d1 is significantly different from Data Items belonging to different groups (B — Z).

Back to our example…

Our quiz was an example of Supervised Learning — Regression technique.

Some common applications of Machine Learning that you can relate to:

  1. Your personal Assistant Siri or Google uses ML.
  2. Weather predictions for the next week comes using ML.
  3. Win Predictor in a sports tournament uses ML.
  4. Medical Diagnosis dominantly uses ML.
  5. And something you would be familiar with, ever wondered how come media sites shows you recommendations and ads matching closely to your interests? They as well use Machine Learning.