[axiom]

Oy! enough with the neural networks already.

Look, a neural network is not some magic machine that can solve all your classification problems. A good 90% of applications of ANNs I've seen could (read: should) have been replaced with a support vector machine, or a Bayesian classifier, or some other proper statistically principled model.

I swear, I get the impression that people keep coming back to ANNs just because the goddamn name sounds cool.

[jcbozonier]

Some of us just don't know what they are or how to use them. I guarantee I'll be forming another study group some time in the future on the other topics you mentioned if they are as broad in application as you say. :)

[axiom]

My advice would just be to take a few stats courses. Make sure you're comfortable with your linear algebra inside out. Learn as many numerical methods as possible etc. etc.

In my mind, neural networks should only be used when you're trying to model actual biological systems. Otherwise, one should always use a proper model - since it actually gives insight into what's going on with the system, instead of just being a magic black box. Of course, notice that all commonly used ANN topologies have nothing to do with biology - feed forward, hopfield nets, kohonen maps etc. They have barely any resemblance to how actual neurons behave. Basically, they are just heuristics with a cool sounding name.

[designtofly]

I completely agree with you! The same should be said for genetic algorithms. I don't understand the obsession around here with both ANN and GA. They are interesting tools, but they are not some holy grail with unlimited applications.

Both of them are inefficient and rarely the right tool for the job. GA and ANN are used for situations where you don't care about how you got to the solution and what it took to get there, as long as you get close to it in the end.