Hey, thanks for the "*COMPETENT PROGRAM EVOLUTION*" paper. I'll take a closer look at that.
And I too think using reference material is a good start. The only clear outline of the backprop algorithm I found was in this paper: page.mi.fu-berlin.de/rojas/neural/chapter/K7.pdf. I haven't found a paper or text with good datasets. If you know where I can get some other good data sets, that have been used in a backprop system, I'm keen to get my mitts on them :) The only other dataset I had my eye on was the sun spots as seen in the encog Clojure wrapper<https://github.com/jimpil/enclog/blob/master/src/java/PredictSunspotSVM.java>. So I think that'll help. Thanks Tim On Mon, Nov 19, 2012 at 10:49 AM, Andreas Liljeqvist <bon...@gmail.com>wrote: > If you have too many neurons or not a big enough dataset, you risk > learning the features of the trainingset but not the generality of the > problem. > > [e1 e2 answer] > (def dataset[[1 1 2] [2 2 4] [4 4 8]]) > > Are you learning addition here or a doubling function? > > If you have enough neurons, you could also more or less encode a lookup > function instead of the logic behind it. > eg. > (defn func [x] ({[1 1] 2 [2 2] 4} x)) ; yeah I would not look like this if > I was encoded in a NN. > instead of: > (defn func [x] (apply + x)) > > It will break down once it finds data not in the trainingset. > > About the validation of your implementation. > Try to find a textbook where they are calculating a simple backprop > network by hand. > Steal their data and make unit tests from it. > > > -- You received this message because you are subscribed to the Google Groups "Clojure" group. To post to this group, send email to clojure@googlegroups.com Note that posts from new members are moderated - please be patient with your first post. To unsubscribe from this group, send email to clojure+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/clojure?hl=en
