“Brain-inspired” and “nature-inspired”, a rant.
Look at this press release Lockheed Martin to Develop Automated Object Recognition Using Brain-Inspired Technology. To be inspired by brain they would need to understand how it works. Do they, really? Where did they stash their Nobel prize? Apparently, they know how a person looking at an apple forms the word ‘apple’ in his brain. If a scientist made such a claim, it would be immediately challenged - by other scientists. But as long as this is a “technology”, people will believe anything. And some (DARPA) even pay money for it!
This is also a part of another pattern – trying to emulate nature to create new technology. The idea is very popular but when has it ever been successful? Do cars have legs? Do planes flap their wings? Do ships have fins? What about electric bulb, radio, phone? It’s silly to think that computers will be an exception. End of rant.
October 24th, 2007 at 10:26 pm
A follow-up. One example when an AI problem was solved by NOT following the way people think was Deep Blue. The program beat Kasparov by relying, essintially, on brute force computation.
November 2nd, 2007 at 2:32 pm
[…] Another point was about training and machine learning. I have big doubts about the whole thing. It is very much like trying to imitate the brain (or something else we observe in nature). Imagine you have a task the people do easily but you don’t understand how they do it. Now you solve the problem in these three easy steps. […]
February 17th, 2008 at 11:38 pm
Another follow-up. Apparently, some researchers developing artificial heart stopped trying to imitate human heart (ventricles etc) and go with more familiar engineering designs.
March 23rd, 2008 at 6:00 pm
[…] I liked this recent blog post 10 Important Differences Between Brains and Computers. The reason is that it gives plentiful evidence in favor of my contention that in designing computer vision systems one shouldn’t try to imitate the human. There are two main reasons. Firstly, computers and brains are very different. Secondly and more importantly, we don’t really know how brains operate! […]
May 20th, 2008 at 3:20 pm
First of all, just because computers and brains operate differently on the implementation (hardware vs. bioware) level doesn’t mean that the algorithms and representations used by our brains won’t be useful for developing better computer vision systems. Secondly, we do indeed already know a fair amount about how vision works in the brain, and we’re learning more all the time. So while we’d probably never want to build a computer vision system that mimics the brain at the synaptic level, we should be ready to take advantage of our expanding knowledge of biological vision rather than saying brains are too different or too complicated and sticking our heads into the sand.
May 20th, 2008 at 10:13 pm
David>> Computer vision is a science. Just like any science it tries to understand the world around us. What is suggested is that we should instead try to understand — how we understand the world. It’s a roundabout, at best.