As you have been progressing towards building AI readiness, you must have come across a very common dilemma between Artificial Intelligence (AI) and Machine Learning (ML).

Many times, these terms are used interchangeably but are they the same? Is there no difference in Machine Learning and Artificial Intelligence? Is Deep Learning (DL) Also Artificial Intelligence? What exactly is Deep Learning? Let us see

This Flow chart will help us get the overview of Artificial Intelligence

/images/aishortFlowChart.png

To read about Artificial Intelligence Go to What is AI & What Not ? and Human vs Artificial Intelligence

Now you should be sure about what AI is, So we can jump to what is Machine learning below.

What is Machine learning

It is a subset of Artificial Intelligence which enables machines to improve at tasks with experience (data).

The intention of Machine Learning is to enable machines to learn by themselves using the provided data and make accurate algorithms for Predictions/ Decisions.

Now lets understand Machine Learning in a simple way. In literal Machine Learning is "Machine" + "Learning".

It means that Associating Machines with Learning. Lets go dig it out :)

How Machine Learning works ?

Machines Learn in a similar manner in which humans learn. Well Lets quickly see How Humans Learn ?

How Humans Learn ?

To understand the human learning process, let us illustrate it through a simple sequence of activities involved.

/images/human-learning-process-class-10.JPG

Machine Learning Process

A computer learns in a similar way. However, it needs a lot of information, to ensure that it recognizes things accurately. Machines need to be trained to make decisions and to act based on goals

How to Train Machines ? Computers need a lot of information to ensure accurate recognition of things

Lets Take an Example , Now think, how can a computer recognize a flame?

This could be using color, size, shape, origin, temperature, etc. Once it recognizes the flame, it needs to be trained to make the decision to act, as in this case, whether it should touch the flame or not?
This is based on the goals set for the computer.

For example, a computer set the goal to extinguish the flame by touching or stamping. So, it will see a flame and act to touch it and extinguish it, whereas another way to avoid burning and damage is to see a flame as danger and not to touch it.

Now think, how will a computer differentiate between an actual flame and a photo of the flame?

A wrongly trained computer may try and extinguish the flame in the painting or touch a live flame again to get damaged. So, is it possible that they can discern based on temperature, movement, etc?

Capability of Machines

To make the machine learn, first we need to see the capability of the machine.

Capabilities of a Machine:-


  1. Cameras for capturing images.
  2. Receivers for capturing sound.
  3. Convertors and Speakers to produce sound.
  4. We Can provide them with sensing devices that can act like skin, eyes, ears, mouth, and noses . Some of these are called sensors.
  5. Sensors are man-made (artificial) devices, usually made of specific materials and connected using electronic signals. They sense chemicals, waves, light, and other things and interpret them

Artificial Intelligence vs Machine learning

What is Deep Learning

Machine Learning vs Deep learning