Live data from Hacker News

Neural Networks Virtual Study Group

groups.google.com

1–10 of 12 posts

Re: Neural Networks Virtual Study Group

#3
post #2

Seems like a great idea. Would be cool to see more of these... Of course C# seems like a horrible choice for learning about this sort of stuff, but maybe that's just me.

Yeah, these distributed courses are a great idea.

There's a bunch of free textbooks online, especially for CS and math topics. I'd love to see online communities develop around the textbooks for like-minded people to form study groups.

Re: Neural Networks Virtual Study Group

#4
post #2

Seems like a great idea. Would be cool to see more of these... Of course C# seems like a horrible choice for learning about this sort of stuff, but maybe that's just me.

I was thinking the same thing as well. It would be great to see more of these done in different languages for various topics.

Re: Neural Networks Virtual Study Group

#7
post #2

Seems like a great idea. Would be cool to see more of these... Of course C# seems like a horrible choice for learning about this sort of stuff, but maybe that's just me.

hmm, i don't really think C# has anything to do with it, other than just providing a vehicle for implementation of fundamental ideas of NN theory (imho ofcourse).

in my opinion, using mathematica (or some such) would have been a far saner choice, to get to the essence of the subject. also, a dosage of classical (pioneering ?) work as described in (parallel-distributed-processing vol-1&2) http://www.amazon.com/Parallel-Distributed-Processing-Vol-Fo..., would be just great.

Re: Neural Networks Virtual Study Group

#8
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.

Re: Neural Networks Virtual Study Group

#9
post #8

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 th…

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. :)

Re: Neural Networks Virtual Study Group

#10

question: where else can i learn about neural networks and ai?

my recommendations (for neural networks) would be as follows:

   - parallel distributed processing (PDP group vol 1 & 2)
   - simon haykin (Neural Networks and Learning Machines)
   - christopher bishop (Neural Networks for Pattern Recognition)
Post reply on HN