“Maybe the only significant difference between a really smart simulation and a human being was the noise they made when you punched them.” ― Terry Pratchett, The Long Earth
Adhyayam – 1 [Chapter – 1 (Sanskrit)]
Artificial Intelligence is the future! It is an undeniable verity. Most of us would have heard or read about the annexation of Deep Mind Technologies , a mysterious AI company researching on Machine Learning by Google.inc early this year for $400 million. It was started in just 2011 and rose up to be one the most advanced AI companies albeit its clandestine work. So, there is an immense scope and need for AI.
What is AI?
I would state it this way : ” Any Algorithm or a procedure, which is capable of making rational decisions for various external stimuli“. Well, that was short and precise wasn’t it? Just for a comparison, i will give you the widely accepted definition :
“The automation of activities that we associate with human thinking, activities such as decision making, problem solving, learning, …” – Bellman, 1978.
Now the reader should observe that in my definition, i was completely generic.Since the definition of AI by Bellman in 1978, there has been many fields introduced in AI such as visual perception, speech recognition, language processing, game playing. And notice the word automation. AI need not be an automation. We have loads of softwares that come under AI. The most important aspect of my definition is that i adhere to AI being capable of making only decision and that suffices. All others are just another way of saying the same. In game playing, you make decisions as to what the next optimal move should be, in language processing, you make decisions as to how to interpret the phrase and what is the suitable reply. In machine learning, you again choose the aspects that are to be incorporated in the next generation trials and their utility. I also believe that the various other aspects of AI like Logic, reasoning, are also specific cases of decision making process.
Now the world has forged ahead from just pondering over the idea of the evolution of human intelligence to imparting it to machines. Each machine is a brain child of its creator. Now scientists try to assay the development of human intelligence through imparting intelligence to machines. Now a question arises, how close are the current AI algorithms to human cognition?, well not quite close but there has been tremendous furtherances in AI.
Okay.. so where are your fancy AI machines in the market?? Well, does Siri ring a bell? Google Now?. These are the products of natural language processing researches, one of the main domain in AI. AI is extremely vast and new kinds of intelligence are constantly budding up.
I would like to share some of the AI projects, which i feel are amazing and each is a work of art. I shall share 4 things which are jargon but everyone needs to know
- Kilobots : These are tiny mobile robots which are engineered to demonstrate collective behaviours algorithms. Literally there are 1024 of them. These are useful for studying the swarm behaviour and implementing them in robotics for doing tedious tasks through intercommunicating bots. Developed by Self-Organizing systems research group at Harvard University. Their main aim is to control these 1000+ bots for various procedures like shape formation, contour tracing and localisation.
- Wolfram Alpha : Some of you would have known about it but still, This is a computational knowledge engine. Well that’s how they call it. To put it in simpler terms, it is a search engine, which apart from from googling the answer (oops!) i meant searching the answer, it also computes the answer. Have a tough calculus problem? just put it in the wolfram alpha search bar and viola!! get the answer, the plot and various other relevant data! Compared to it, Google search is… just lol! Well, try it till you feel the amazement. Here are some sample pictures of it.
Wolfram Alpha does not just add the directories of the websites . but it relies on licensed data catalogues by its employees, that are as accurate it can ever be. Unlike a normal search engine, it does not give you pictures of celebrities but rather gives you factual answer as well as its visual interpretation. (Phew!! Google is out of danger!..hmmm..maybe).
- Blue Brain Project : It is a project aiming to reverse engineer the brain. It reconstructs the brain ‘piece by piece’. The cortex in the brain is the most evolved and advanced technology created by nature, and this project aims to virtually simulate that. They initially started with a rat’s brain and have successfully using 100 mesocircuits, and by 2023, they have planned to recreate the human brain which is equivalent too 1000 rat brains.To further the understanding they have planned to simulate at a molecular level to study the chemistry behind cognition.
- A.L.I.C.E : It is an acronym for “Artificial Linguistic Internet Computer Entity” is a chatterbot, means you can have a conversation with a computer that uses natural language processing. It is an open source software. The researches created a XML-compliant language called AIML (AI markup language) in which even users can customize their chatterbox.
I don’t think i need to explain about IBM’s two most mind-blowing machines Deep Blue and Watson.
So, after this quite a lengthy introduction to AI, we shall come to the topic, what is entropy? and How is it even related to AI?.. That will be in the next Adhyayam!!
“You should never be surprised by or feel the need to explain why any physical system is in a high entropy state.”
― Brain Greene, The Fabric of the Cosmos
For Further Readings :
Kilobots : http://spectrum.ieee.org/automaton/robotics/robotics-hardware/a-thousand-kilobots-self-assemble http://www.eecs.harvard.edu/ssr/projects/progSA/kilobot.html
Wolfram Alpha : http://computer.howstuffworks.com/internet/basics/wolfram-alpha1.htm http://www.wolframalpha.com/
Blue Brain Project : http://bluebrain.epfl.ch/page-52063.html