Re: ANN vs. nonlinear regression: forecasting
Rich, You are generally right that a NN is basically a logistic regression. Although one could get bogged down in an argument surrounding that. To answer the original question. Brian Ripley's book on pattern recognition and NN is not exactly right but I feel thats its in the right vein of thinking. It worth a look. I have seen a number of papers around the subject of NN and Time Series. Go to http://www.maths.uq.edu.au/~gks/webguide/index.html its an excellent site and should help you in explorer the web for this question Cheers Mark Young [EMAIL PROTECTED] Rich Ulrich <[EMAIL PROTECTED]> wrote in message [EMAIL PROTECTED]">news:[EMAIL PROTECTED]... > On Fri, 11 Feb 2000 15:01:25 GMT, [EMAIL PROTECTED] wrote: > > > I'm working on a study that compares neural networks to classical non- > > linear statistical estimators in forecasting time series. My thesis is > > that the NN would be robust under conditions where the assumptions of > > the classical model are not met, and the nn would be inferior where the > > classical assumptions are satisfied. > > > > What would be a good classical model to compare a neural network to? > > Does anyone know of any papers/sources on this subject? > > Warren Sarle has written an FAQ on neural nets -- see the related > Usenet groups, or see my FAQ for a reference to it. > > Basically... practically every NN *is* a classical model, so your > question is not well-posed; it is fundamentally wrong in its > assumptions. One NN is a logistic model, once you open up the black > box. Another is simple discriminant function. And so on. > > -- > Rich Ulrich, [EMAIL PROTECTED] > http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, people lacking respect for other members of the list send messages that are inappropriate or unrelated to the list's discussion topics. Please just delete the offensive email. For information concerning the list, please see the following web page: http://jse.stat.ncsu.edu/ ===
Re: ANN vs. nonlinear regression: forecasting
On Fri, 11 Feb 2000 15:01:25 GMT, [EMAIL PROTECTED] wrote: > I'm working on a study that compares neural networks to classical non- > linear statistical estimators in forecasting time series. My thesis is > that the NN would be robust under conditions where the assumptions of > the classical model are not met, and the nn would be inferior where the > classical assumptions are satisfied. > > What would be a good classical model to compare a neural network to? > Does anyone know of any papers/sources on this subject? Warren Sarle has written an FAQ on neural nets -- see the related Usenet groups, or see my FAQ for a reference to it. Basically... practically every NN *is* a classical model, so your question is not well-posed; it is fundamentally wrong in its assumptions. One NN is a logistic model, once you open up the black box. Another is simple discriminant function. And so on. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, people lacking respect for other members of the list send messages that are inappropriate or unrelated to the list's discussion topics. Please just delete the offensive email. For information concerning the list, please see the following web page: http://jse.stat.ncsu.edu/ ===
Re: ANN vs. nonlinear regression: forecasting
John -- Sounds very interesting-- If you mean "classical" least-squares model, there are no assumptions involved in fitting least-squares. It's only the "statistics" assumptions that get added into the extra "assumptions". PREDICTION is the important thing. Compare the PREDICTIVE accuracy/costs/etc.of various approaches. You may wish to include RESAMPLING/BOOTSTRAP/CROSS-VALIDATION in your research. The proof of the "best" is how well it PREDICTS I will be interested in what you learn. -- Joe * Joe Ward Health Careers High School ** 167 East Arrowhead Dr 4646 Hamilton Wolfe ** San Antonio, TX 78228-2402 San Antonio, TX 78229 ** Phone: 210-433-6575 Phone: 210-617-5400 ** Fax: 210-433-2828 Fax: 210-617-5423 ** [EMAIL PROTECTED] ** http://www.ijoa.org/joeward/wardindex.html * - Original Message - From: <[EMAIL PROTECTED]> To: <[EMAIL PROTECTED]> Sent: Friday, February 11, 2000 7:01 AM Subject: ANN vs. nonlinear regression: forecasting | I'm working on a study that compares neural networks to classical non-| linear statistical estimators in forecasting time series. My thesis is| that the NN would be robust under conditions where the assumptions of| the classical model are not met, and the nn would be inferior where the| classical assumptions are satisfied.| | What would be a good classical model to compare a neural network to?| Does anyone know of any papers/sources on this subject?| | I sincerely appreciate any help/suggestions.| | John Carrier| [EMAIL PROTECTED]| | | Sent via Deja.com http://www.deja.com/| Before you buy.| | | ===| This list is open to everyone. Occasionally, people lacking respect| for other members of the list send messages that are inappropriate| or unrelated to the list's discussion topics. Please just delete the| offensive email.| | For information concerning the list, please see the following web page:| http://jse.stat.ncsu.edu/| ===|
ANN vs. nonlinear regression: forecasting
I'm working on a study that compares neural networks to classical non- linear statistical estimators in forecasting time series. My thesis is that the NN would be robust under conditions where the assumptions of the classical model are not met, and the nn would be inferior where the classical assumptions are satisfied. What would be a good classical model to compare a neural network to? Does anyone know of any papers/sources on this subject? I sincerely appreciate any help/suggestions. John Carrier [EMAIL PROTECTED] Sent via Deja.com http://www.deja.com/ Before you buy. === This list is open to everyone. Occasionally, people lacking respect for other members of the list send messages that are inappropriate or unrelated to the list's discussion topics. Please just delete the offensive email. For information concerning the list, please see the following web page: http://jse.stat.ncsu.edu/ ===
