Learning abilities of computers and humans

While commenting on the comments to my previous note (see here), I thought about the comparison of human and computers in terms of learning performance. Does this comparison even make sense? If it does, on which basis, or with which criteria can it be made?

If you adopt a purely theoretical point of view, the no free lunch theorem tells you that you just cannot compare two learning machines in general. So all comparisons should be based on a specific, restricted set of reference problems.

If you adopt a Bayesian point of view, learning is very easy: once you have chosen your prior (an likelihood function), it is just matter of computation to get the posterior. So that, again, you cannot compare two learning machines, you can only compare their priors. Their performance will be more or less directly related to how well the prior matches the problem at hand (i.e. how high is the prior probability of the problem to be learned).

So we may already have very efficient learning algorithms (probably even better than the brain because they can compute more precisely and much faster -- although one can discuss what computing means in this context), and we still believe computers are not able to match humans learning performance because we compare them on tasks for which humans have much better priors.

Of course I am not saying anything new here: Bayesians would tell you that this has always been clear for them, you only have to build a good prior and you are done.

But building a good prior is not an easy task: it requires to define the right features, to find the right notion of smoothness... and there is basically no guidance for this! Moreover, it is completely problem-specific. So, apart from helping to implement Bayes rule efficiently, general (i.e. application-independent) Machine Learning research cannot help much.
One could then draw the conclusion that the essence of the learning problem is not statistical but computational.

But I still think there are important statistical problems, and I will come back to this issue in a future note...

Comments

[PierreD]

Hi,

A way to get priors for a problem can be to re-use some knowledge from other similar issues.

This kind of "transfer learning" is applied in this paper:

http://www.icml2006.org/icml_documents/camera-ready/090_Constructing_Informa.pdf

The good point of bayes rule is that some posteriors can become prior for another problem. Placing this feature on a time line (ie the life of the learning agent), we can imagine the agent starting with poor prior and refining, generalizing it after experience.
It reminds me the field of "developmental robotics" were agents have a strategy to choose new problems on wich they can learn a lot.

Cheers,
Pierre

[Buy Research Paper]

looks quite a great post, it's having good information for research analysis. great job

[Buy Research Paper]

looks quite a great post, it's having good information for research analysis. great job

[Term Papers]

Very nice write up. Easy to understand and straight to the point.

[Generic Viagra]

I think you are doing a great job with the design and content in this site,I am so interested on what I read and I am curious to find out more about Buying & Selling eContent

[online viagra]

computers and humans who is very powerful obviously human being because human
has created the computer.

....Alex

[commenting system]

Well...the best thing that every human has and the machine not is only Laziness :) nothing do to do!

[cheap jordans]

Never leave that until tomorrow, which you can do today.

[air jordan]

None of the turmoil that routinely attends film-star existence ever seemed to visit the Astaire household.

[software testing]

I like your post a lot.It raises interesting facts and figures.I agree that computers reduces lot of our work but still Humans are superior to computer whether it is about learning abilities or any other things.This information is helpful to know computers and human better.Thanks for such informative post.

[kevin kirkwood]

Testing was a success and everything works fine.

[buy cialis]

The things that computer and animals differentiate one from another is that we can adopt different way to learn something that in the go (adaptation).

[buy xanax]

Please one more post about that.I wonder how you got so good. This is really a fascinating blog, lots of stuff that I can get into. One thing I just want to say is that your Blog is so perfect

[Monster High Dolls]

So who's smarter now?, human or computers? :)

Cheers

[download flag]

i will reply monster high dolls question.. i think human is still smart than computer. computer need input to to somenthink.

[Timberland Store]

So cute! I already like you on FB and also get your posts on Google Reader. :)