Machine Learns Games 241
heptapod writes "New Scientist is reporting that UK researchers have created a computer that can learn rock, paper, scissors by observing humans. CogVis uses visual information to recognize events and objects in addition to learning by observing."
-0.5 half right... (Score:3, Informative)
So the computer sees "Scissors-Paper" a few times and then always queus up the "Left Wins" response when it sees "Scissors-Paper" in the future. That's just a different method of programming.
Now, if only 6 of the 9 possible hands had been played, and then a 7th hand the computer hadn't seen before was played and the computer could tell you who won that, that'd be something. This is just record and playback.
Re:Better be reliable... (Score:4, Informative)
Granted, the parent poster is being silly, but that's actually not too far from what they did. They basically took the system and pointed it towards the people playing the game without telling it explicitly what to expect. From the article:
Chris Needham, another member of the CogVis team, says the system's visual processor analyses the action by separating periods of movement and inactivity and then extracting features based on colour and texture. Combining this with audio input, the system develops hypotheses about the game's rules using an approach known as inductive logic programming [wikipedia.org].
"It was very impressive," says Max Bramer, a researcher at Portsmouth University, UK, and chair of the British Computer Society's AI group. He told New Scientist that CogVis could have many future applications. "You can think of lots of times when you'd like to be able to point a camera at something and have a computer interpret things for itself."
He suggests that machine's could one day use this technique to learn how to spot an intruder on video footage or how to control a robot for important maintenance work. "It's a very good start, and almost mysterious in the way it works," Bramer adds.
From their page:
In this piece of work we are attempting to learn descriptions of objects and events in an entirely autonomous way. Our aim is zero human interference in the learning process, and only to use non scene specific prior information. The resulting models (object and protocol) are used to drive a synthetic agent that can interact in the real world.
Industrial accidents (Score:3, Informative)
The problem is precisely the lack of free will and independent thinking. A machine has grappling hooks, vacuum suction or serving belt, but it can not make value judgment on what/whom it is throwing into molten metal.
As the AI develops, the problem will get worse before it gets better. A robot working in slaughterhouse might have the ability to chase a running mammal and cut it's throat, but not to ascertain exact species. Imagine a beowulf cluster of those on the run in New York subway. Workspace and consumer safety legislation would be very much in order at that point.
More info in research publications (Score:5, Informative)
Towards an Architecture for Cognitive Vision Using Qualitative Spatio-temporal Representations and Abduction [springerlink.com] (Cohn et al, 2003)
Modeling interaction using learnt qualitative spatio-temporal relations and variable length Markov models [google.com] (Galata et al, 2002)
Re:is this really all that new? (Score:4, Informative)
It's bloody amazing, the amazing bit being it deduces how to play from first principles, starting with just the ability to identify that what it's being shown is an object.
Takes about 30 minutes to get rolling, but it really is stunning to watch! Hell, object differentiation is hard enough, deducing the rules of play, and tactics as well?
Re:-0.5 half right... (Score:1, Informative)
It might be amusing to see what would happen if you tried to feed the system duplicate (or even contradictory) training material. Would it assign a probability for each 'correct answer' and then randomly select one? Or would it try to select based on the previous round(s)? Any speculation I make is worthless, since they could change the 'learning model' at any time.
(*) The part of this demonstration that actually somewhat impresses me is the ability of the system to recognize the cards in arbitrary orientations on the table. (Granted, it's only recognizing simple/nonsimilar patterns in black and white, but that's still the most impressive part of this project.)
Re:Intruder (Score:2, Informative)
Re:language? (Score:2, Informative)
Re:Profit! (Score:2, Informative)