Branches of Artificial Intelligence (AI) – Part 1
Artificial intelligence (AI) is not new, though in recent years it has created hype. Due to its relation to automation; which a lot of people relate to job reduction (although I don’t think so) as a result, AI is suddenly in the lamplight!
Does AI really matter to us? Surely, many legends are talking about it…
The development of full artificial intelligence could spell the end of the human race. It would take off on its own, and re-design itself at an ever-increasing rate. Humans, who are limited by slow biological evolution, couldn’t compete and would be superseded.
— Stephen Hawking
Here is an attempt to unleash various aspects of AI. Lets first analyze, what AI really is?
Artificial intelligence is an area of computer science, which emphasizes the creation of intelligent machines that work and react like humans.
In a simple language, AI is the ability of a computer program or a machine to think and learn. Which tries to make computers “smart“. As a result, the computer can see, explore, learn, adapt, respond, hear, behave and communicates like humans.
Branches of AI
There are various branches of AI, just like humans got senses to see, hear etc. The below image shows various subsets of AI.
What is Machine Learning? According to Arthur Samuel in 1959, Machine Learning gives “computers the ability to learn without being explicitly programmed.”
In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it.
Lots of people get confused with AI, ML and Deep Learning.
Machine Learning is the subset of Artificial Intelligence, that deal with the extraction of patterns from data sets.
This means that the machine can find rules for optimal behavior, but also can adapt to changes in the world.
Many of the algorithms involved have been known for decades, centuries, even. Thanks to the advances in computer science and parallel computing they can now scale up to massive data volumes.
Deep Learning, on the other hand, is a specific class of Machine Learning algorithms which use complex neural networks.
Below image can bring more clarity on what I am talking about!
Natural Language Processing
The field of study that focuses on the interactions between human language and computers is called Natural Language Processing, or NLP for short.
NLP is a way for computers to analyze, understand, and derive meaning from human language in a smart and useful way.
By utilizing NLP, developers can organize and structure knowledge to perform tasks such as automatic summarization, translation, named entity recognition, relationship extraction, sentiment analysis, speech recognition, and topic segmentation.
In 1971, Terry Winograd wrote the SHRDLU program while completing his Ph.D. at MIT. SHRDLU features a world of toy blocks where the computer translates human commands into physical actions, such as “move the red pyramid next to the blue cube.” To succeed in such tasks, the computer must build up semantic knowledge iteratively, a process Winograd discovered was brittle and limited.
There are 4 ways, by which we can approach NLP, which are:
4) Interactive learning
You can learn more about this here
The below video from Youtube can explain more about NLP and how it is associated with different subsets of AI.
To know more about remaining part of AI, like robotics, vision, expert system and speech; do read part 2 of this article ‘Understanding Branches of Artificial Intelligence (AI) – Part 2‘