17
$\begingroup$

From Wikipedia:

A mirror neuron is a neuron that fires both when an animal acts and when the animal observes the same action performed by another.

Mirror neurons are related to imitation learning, a very useful feature that is missing in current real-world A.I. implementations. Instead of learning from input-output examples (supervised learning) or from rewards (reinforcement learning), an agent with mirror neurons would be able to learn by simply observing other agents, translating their movements to its own coordinate system. What do we have on this subject regarding computational models?

$\endgroup$
4
$\begingroup$

This article gives a description of mirror neurons in terms of Hebbian learning, a mechanism that has been widely used in AI. I don't know whether the formulation given in the article has ever actually been implemented computationally.

$\endgroup$
0
$\begingroup$

Whether "I take the ball" or "he takes the ball", all stored instances of 'taking' and 'ball' will be weakly activated and 'taking [the] ball' will be strongly activated. Doesn't this qualify as 'mirroring'? If you also know that "I have an arm" and "he has an arm", etc., then when "he takes some blocks", it isn't too hard to think that "I could take some blocks."

$\endgroup$
0
$\begingroup$

We actually do have many things along that line, motion capture for 3-D movies instance comes to mind almost immediately. The problem if I think about it is less of a situation in observing another actor, computers are relativity good at doing that already with the amount of image recognition software we have, rather it's a problem of understanding if an action yielded a good outcome as a net which is something that computers cannot do as it's not a single node network problem. For example, we've already programmed a computer to understand human language (Watson, arguably), but even Watson didn't understand the concept that saying "f***" is bad. (Look that up, it's a funny side story.)

But the point is, learning algorithms are not true learning in a sense as a computer currently has no sense of "a good outcome", hence at this stage observation learning is very much limited in a sense to "monkey see, monkey do".

Perhaps the closest thing I have ever read about with this was firefighting search and rescue bots that were on a network and would broadcast to each other when one of them had been destroyed as the bots would know the area was something that they had to avoid.

Otherwise, I think this is the problem with observational learning. A person can observe that punching someone usually will get you hit back, a computer will observe and parrot the action, good or bad.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.