http://www.shiffman.net/2006/11/10/multi-layered-neural-network/ Fri, 21 Nov 2008 00:19:39 +0000 http://wordpress.org/?v=2.6 http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-6150 Fergus Ray Murray Wed, 06 Dec 2006 08:57:25 +0000 http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-6150 I love how gratuitously pretty you've made this. :) I'll be curious to see what else you come up with on the Neural Networks In Processing front (especially if you do make a library!) - I expect to be doing some experimenting in this area myself, for academic reasons (see http://www.mimeomai.f2s.com/oolong/ac/ if you're curious). I love how gratuitously pretty you’ve made this.
I’ll be curious to see what else you come up with on the Neural Networks In Processing front (especially if you do make a library!) - I expect to be doing some experimenting in this area myself, for academic reasons (see http://www.mimeomai.f2s.com/oolong/ac/ if you’re curious).

]]> http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-5372 Kyle Mon, 13 Nov 2006 23:17:16 +0000 http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-5372 It think Aaron Steed is in the middle of a backpropagation library already, actually: http://www.robotacid.com/PBeta/AILibrary/ (A more general connectionist library might be cool though, there are some other architectures people would appreciate...) It think Aaron Steed is in the middle of a backpropagation library already, actually: http://www.robotacid.com/PBeta/AILibrary/ (A more general connectionist library might be cool though, there are some other architectures people would appreciate…)

]]> http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-5362 Daniel Mon, 13 Nov 2006 18:49:05 +0000 http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-5362 Thanks for the comments Kyle. After doing some further reading I came to similar conclusions. I'm going to make this example a bit more generic (maybe even turn it into a library) and investigate incorporating "momentum" into the weight changes. . . Thanks for the comments Kyle. After doing some further reading I came to similar conclusions. I’m going to make this example a bit more generic (maybe even turn it into a library) and investigate incorporating “momentum” into the weight changes. . .

]]> http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-5361 Kyle Mon, 13 Nov 2006 18:43:51 +0000 http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-5361 I don't think you've done anything wrong, one of the problems with backpropagation is that it sometimes converges on local minima (this is one of the reasons "momentum" is used during weight change). I get similar percentages of ~66% and ~98%: http://rpi.edu/~mcdonk/code/xor/ (My code allows for a more generic network structure but isn't quite as nicely packaged :) ) I don’t think you’ve done anything wrong, one of the problems with backpropagation is that it sometimes converges on local minima (this is one of the reasons “momentum” is used during weight change). I get similar percentages of ~66% and ~98%: http://rpi.edu/~mcdonk/code/xor/ (My code allows for a more generic network structure but isn’t quite as nicely packaged )

]]> http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-5204 Daniel Sat, 11 Nov 2006 02:28:28 +0000 http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-5204 Train to an error of. . . what?? The suspense is killing me. . . Train to an error of. . . what?? The suspense is killing me. . .

]]> http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-5198 Steve Sat, 11 Nov 2006 00:10:37 +0000 http://www.shiffman.net/2006/11/10/multi-layered-neural-network/#comment-5198 Your network with two hidden nodes should train to a error of Your network with two hidden nodes should train to a error of

]]>