Introduction to Machine Learning and some basic terminology

What is Machine Learning?

As the name is itself self-explanatory machine learning is learning by the machine itself. The concept is, to program a machine in such a way that it can learn from itself.

The computer is not explicitly programmed, it is provided with training data, using which it can predict the output.

Types of Machine Learning.

Machine learning can be classified into 3 types:

  1. Supervised Learning
  2. Unsupervised Learning
  3. Reinforcement Learning

Supervised Learning

In Supervised Learning, we provide the training data in pairs, i.e... for a set of input we provide a set of output.

Example:

For a specific cc of a car engine, you are given the price of the car.

1.png

Now using this training data computer we can predict the expected output value.

2.png

Supervised Learning can further be classified into 2 categories :

Regression :

Predicted output has continuous value as the same example

3.png

Classification :

Predicted output has discrete value as an example

4.png

Unsupervised Learning

In Unsupervised Learning, you are given raw data

As an example

5.png

Like supervised learning, we are not provided with the expected output. We are just given raw data, now we have to find patterns and structures in the given data.

6.png

As an example, we have divided the data input into 2 clusters.

Reinforcement Learning

In Reinforcement Learning the computer learns from mistakes. As an example, you have given the computer pictures of dogs and cats. Now you bring a new image of the dog and the machine identifies it as a cat. So as a feedback mechanism you say that the given picture is of a dog. So the machine understand and try to learn from mistakes

Did you find this article valuable?

Support Vinayak tech Blog by becoming a sponsor. Any amount is appreciated!