The Difference Between Artificial Intelligence, Machine Learning, and Deep Learning

By pratosh |Email | Apr 19, 2018 | 5850 Views

We are all familiar with the term AI and ML. It has been a very popular focus in movies now a days, The Terminator, The Matrix to name a few. You might be coming across terms like ML and deep learning nowadays, sometimes used interchangeably with AI. This diminish the difference between AI, ML and deep learning. 

This article will first give a quick explanation of what AI, ML, and deep learning is and how they are different from each other. Then this article will exlplain how AI and IOT are inextricably interwined with several technologies advance all covering at once to set the foundation for an AI and IOT explosion. 

So what is the difference between AI, ML, and DL?

First coined in 1956 by John McCarthy, Artificial intelligence involves machines that can perform tasks that are characteristic of human intelligence. While this is rather general, it includes things like planning, understanding language, recognizing physical object and audio, learning, and problem solving.

We can put AI in two categories, general and narrow. General would have all of the characteristics of human beings, including the capacities mentioned above. Narrow AI exhibits some facet (s) of human intelligence, and can do that facet extremely well, but is lacking in other areas. A machine that is great at recognizing images, but nothing else, would be an example of narrow AI.

Chester A. Arthur Samuel coined the phrase not too long after AI, in 1959, modelling it as, "the ability to learn without being explicitly programmed". You can get AI without using machine learning, but this would require building millions of personal line of credit of codes with composite prescript and decision-trees.
So instead of hard coding software routines with specific directions to achieve a specific job, machine learning is a method of "training" an algorithm so that it can learnhow. "Training" comprises feeding huge quantities of data to the algorithm and letting the algorithm to change itself and progress.

To give an illustration, machine learning has been used to make radical advances to computer vision (the capability of a machine to identify an object in an image or video). You collect hundreds of thousands or even millions of images and then have humans tag them. For instance, the humans might tag images that have a cat in them against those that do not. Then, the algorithm attempts to build a model that can accurately tag a picture as containing a cat or not as well as a human. Once the correctness level is extraordinary, the machine has now "learned" what a cat looks like.

Deep learning is one of many approaches to machine learning. Other methodologies contain decision tree learning, inductive logic programming, clustering, reinforcement learning, and Bayesian networks, among others.

Deep learning was inspired by the arrangement and function of the brain, namely the connection of many neurons. Artificial Neural Networks (ANNs) are algorithms that parodist the organic structure of the brain.
In ANNs, there are "neurons" which have discrete layers and connections to other "neurons". Each layer picks out a specific feature to learn, such as curves/edges in image recognition. This layering gives deep learning its name, depth is produced by using numerous layers as contrasting to a single layer.

Unleashing Each Other's Potential

The importance and the potential of both AI and IoT are being realized because of the other.
Machine learning and deep learning have led to huge leaps for AI in recent years. As stated above, machine learning and deep learning needs massive amounts of data to work, and the billions of sensors that are continuing to come online in the Internet of Things are composing this data. IoT creates better AI.
Improving AI will also drive acceptance of the Internet of Things, generating a virtuous cycle in which both areas will accelerate radically. That is because AI makes IoT helpful.

On the industrial side, AI can be applied to forecast when machines will need maintenance or investigate manufacturing processes to make big efficiency gains, saving millions of dollars.

On the consumer side, rather than having to adjust to technology, technology can become accustomed to us. Instead of clicking, typing, and searching, we can merely ask a machine for what we need. We might ask for information like the weather or for an action like making the house for bedtime (turning down the thermostat, locking the doors, turning off the lights, etc.)

Converging Technological Advancements Have Made this Possible
Reducing computer chips and improved building-up techniques means cheaper sensors that are more powerful.
Rapidly taming battery technology means those sensors can last for years without demanding to be linked to a power source.
Wireless connectivity, driven by the arrival of smartphones, means that data can be sent in high volume at low-priced rates, letting all those sensors to send data to the cloud.
And the birth of the cloud has allowed for virtually unlimited storage of that data and virtually infinite computational ability to process it.
Of course, there are one or two concerns about the impact of AI on our society and our future. But as progressions and adoption of both AI and IoT continue to accelerate, one thing is certain; the impact is going to be profound.







Source: HOB