Re: Learning Regression Function / Neural Networks

2008-10-20 Thread Ovid
--- On Mon, 20/10/08, Alistair MacLeod <[EMAIL PROTECTED]> wrote: > I suspect a simple backpropagating multilayer perceptron > should do ok > for this but I have not really used these in anger before. > > My questions for the perlmongers: > > 1. Is a perceptron the best approach? How else could

Re: Learning Regression Function / Neural Networks

2008-10-20 Thread Simon Wistow
On Mon, Oct 20, 2008 at 03:56:21PM +0100, Alistair MacLeod said: > I suspect a simple backpropagating multilayer perceptron should do ok > for this but I have not really used these in anger before. That was my thought as well, after a brief read over your mail. The ORA book "Programming Collectiv

Learning Regression Function / Neural Networks

2008-10-20 Thread Alistair MacLeod
Hi, I have a (multi)function of three variables and two outputs that I need to be learnt from examples. The inputs are are slightly correlated with each other. The outputs will also be. The function is not at all smooth - there are many irregular peaks. Training data will be generated as the syste

Re: Dear friend,

2008-10-20 Thread Dominic Thoreau
2008/10/20 Jonathan Stowe <[EMAIL PROTECTED]>: > > Well looking at the original message more carefully, unless Tielman is > actually the spammer himself, then there does appear to be a way of > causing gmail to send messages as a third party to everyone in that > third party's contact list. I was

Re: Dear friend,

2008-10-20 Thread Mark Blackman
On 20 Oct 2008, at 10:24, Jonathan Stowe wrote: Well looking at the original message more carefully, unless Tielman is actually the spammer himself, then there does appear to be a way of causing gmail to send messages as a third party to everyone in that third party's contact list. Indeed, no

Re: Dear friend,

2008-10-20 Thread Jonathan Stowe
2008/10/20 Paul Makepeace <[EMAIL PROTECTED]>: > On Sun, Oct 19, 2008 at 8:11 AM, Jonathan Stowe > <[EMAIL PROTECTED]>wrote: > >> On Sat, 2008-10-18 at 14:27 +0100, Martin A. Brooks wrote: >> > Jonathan Stowe wrote: >> > > Anyone know a good way of stopping joe-jobbed spam which doesn't >> involve

Re: Dear friend,

2008-10-20 Thread Paul Makepeace
On Sun, Oct 19, 2008 at 8:11 AM, Jonathan Stowe <[EMAIL PROTECTED]>wrote: > On Sat, 2008-10-18 at 14:27 +0100, Martin A. Brooks wrote: > > Jonathan Stowe wrote: > > > Anyone know a good way of stopping joe-jobbed spam which doesn't > involve > > > spf and stuff ? > > > > > > > Don't have a catchal