Artificial Intelligence, Machine Learning and Deep Learning, what is what?

In this post, I am hoping we will shed some light on these topical concepts, that although are usually used interchangeably, they do not quite refer to the same things.

The main idea behind these three concepts, lie in the image below:

As you can see, Deep Learning (DL) is a subset of Machine Learning (ML), which is also a subset of Artificial Intelligence (AI).

Let’s dig deeper so that we can understand better what each of them three concepts encompass.

Artificial Intelligence:

As the name suggests, artificial intelligence can be interpreted as incorporating human intelligence to machines.

Whenever a machine completes tasks based on a set of stipulated rules that solve problems (algorithms), that behaviour is what is called artificial intelligence.

We classify AI-powered machines into two groups; general and narrow.

The general artificial intelligence machines can intelligently solve problems, for example, moving or manipulating objects, recognizing whether someone has raised the hands, or solving a mathematic problem.

The narrow intelligence AI machines can perform specific tasks very well, sometimes better than humans can; however, they are limited in scope. The technology used for classifying images on Pinterest is an example of this.

Machine Learning:

As we already saw, ML is a subset of AI (in fact it is just a technique for realizing AI) and can be loosely described as ability of the computer systems to learn. 

The intention of ML is to train algorithms to enable machines to learn by themselves how to make decisions.

Training in machine learning entails giving a lot of data to the algorithm and allowing it to learn more about the processed information.

For example, below is a table that identifies the type of fruit based on certain characteristics:

As you can see on the table above, the fruits are differentiated based on their weight and texture.

However, the last row gives only the weight and texture, without the type of fruit. A machine-learning algorithm can be developed to try to identify whether the fruit is an orange or an apple.

After the algorithm is fed with the training data, it will learn the differing characteristics between an orange and an apple and predict accurately the type of fruit with those characteristics in the future.

Deep Learning:

As earlier mentioned, deep learning is a subset of ML; in fact, it’s simply a technique for realizing machine learning; DL is the next evolution of machine learning.

DL algorithms are inspired by the information processing patterns found in the human brain. Just like we use our brains to identify patterns and classify various types of information, deep learning algorithms can be taught to accomplish the same tasks for machines.

The brain usually tries to decipher the information it receives. It achieves this through labelling and assigning the items into various categories.

Whenever we receive a new information, the brain tries to compare it to a known item before making sense of it which is the same concept deep learning algorithms employ.

Comparing deep learning vs machine learning can help to understand their differences. While DL can automatically discover the features to be used for classification, ML requires these features to be provided manually.

Hopefully you are now slightly more clear about what each of these concepts mean and how they are interlinked!