Robots that reason
Apparently some boffins (love that word) at Aberystwyth University in Wales have created a robot called Adam that can not only carry out experiments on yeast metabolism but also reason about the results and plan the next experiment.
A robot that can reason? Is this a case of an over-eager reporter or should we start looking for the obligatory BSG reference to insert here?
More info here.
edit:oops just noticed the typo in the title
[Edited by - ChaosEngine on April 2, 2009 5:34:54 PM]
if you think programming is like sex, you probably haven't done much of either.-------------- - capn_midnight
[size="1"][[size="1"]TriangularPixels.com[size="1"]] [[size="1"]Rescue Squad[size="1"]] [[size="1"]Snowman Village[size="1"]] [[size="1"]Growth Spurt[size="1"]]
That link works best with Firefox
Robots have shiny metal posteriors which should not be bitten.
Robots have shiny metal posteriors which should not be bitten.
"I thought what I'd do was, I'd pretend I was one of those deaf-mutes." - the Laughing Man
I'd like to know how they did it. Is it just a 'dumb' script full of conditional arguments, or is it something like an artificial neural network? In other words, have they actually programmed 'creativity'? Could their AI learn how to write code and thus create a new AI or even just a simple program it initiated on its own?
Eric Nevala
Indie Developer | Spellbound | Dev blog | Twitter | Unreal Engine 4
In similar news, you'll like this: Computer Program Self-Discovers Laws of Physics
Quote: Developed by Cornell researchers, the program deduced the natural laws without a shred of knowledge about physics or geometry.
...
The program started with near-random combinations of basic mathematical processes — addition, subtraction, multiplication, division and a few algebraic operators.
Initially, the equations generated by the program failed to explain the data, but some failures were slightly less wrong than others. Using a genetic algorithm, the program modified the most promising failures, tested them again, chose the best, and repeated the process until a set of equations evolved to describe the systems. Turns out, some of these equations were very familiar: the law of conservation of momentum, and Newton's second law of motion.
"It's a powerful approach," said University of Michigan computer scientist Martha Pollack, with "the potential to apply to any type of dynamical system."
....[size="1"]Brent Gunning
This topic is closed to new replies.
Advertisement
Popular Topics
Advertisement