top | item 12387197

(no title)

alphonse23 | 9 years ago

ANN are not that big of a deal, IMHO, when you compare them to other machine learning techniques i.e. Support Vector Machines. Also, see https://en.wikipedia.org/wiki/Artificial_neural_network#Theo...

Though, this article is so well presented, it deserves an awards for how pretty it is.

discuss

order

Anm|9 years ago

My gut thinks this sort of training alternative to back propagation has a lot of uses where SVM have no applicability. The article talks a lot about RNNs (neural nets for sequence prediction), but I would guess it would have uses in online learning as well. Learning twice as fast in those situations seems pretty significant to me.

alphonse23|9 years ago

I can't believe I'm getting down-voted just because I'm not bullish on ANN.

As I said, in my humble opinion (IMHO), (and educated opinion) NN don't really have a lot of practical use. So long as they have to be processed in parallel, SVM will always have the advantage that they can be computed sequentially, meaning they can process much faster and without the need for specialized hardware. SVMs and ANN are solving the same problem in machine learning, they're both methods used for classifying data. Just SVMs do it much faster and within more practical means.