I. Announcing the New AI Trilogy ™
Maybe you or someone in your company can relate to the following problem. Your company is formulating some mixture: maybe a drug, a bonding compound, an animal feed, foodstuff or beverage, plastic or other packaging material, cosmetic or perfume, lubricating compound, cleaning compound or solvent, paint, insecticide or herbicide, a manufactured item or process, or even problems such as marketing strategies. Your boss or your client has given you the job of finding the optimum mixture of components or process variables, the combination of components and processing methods that produces the best product (components are the percentages of each of the elements of the mixture and the process variables are factors in the building process such temperature, curing time, etc.).
Sound familiar? You don’t even know how the various factors interrelate, much less how to discover the best ones. What do you do? We call this problem the “AI Trilogy” problem, and we believe it is becoming a very common problem in industry today! Fortunately it is quite easy and inexpensive to solve if you have the right tools and the “know how.”
We are proud to announce the AI Trilogy(TM), a new packaging of our most popular business and scientific software. The AI Trilogy contains the NeuroShell Predictor and NeuroShell Classifier neural net software, and GeneHunter genetic algorithm (GA) software together as one package. To make sure you can solve some exciting combination projects like the AI Trilogy problem, we have also thrown in the NeuroShell Runtime Server to go with the Predictor and Classifier. You’ll have all the tools you need to set up and exciting Artificial Intelligence Center at your company. You can solve the AI Trilogy Problem. Best of all your company will save almost $500! Yes, if you purchased the components in the AI Trilogy separately, you’d pay $1480. The AI Trilogy costs only $995!!
So how does the AI Trilogy help you solve the AI Trilogy problem? There are two steps you need to accomplish: 1) model the process with the neural nets so that the interrelationships between the components and process variables are in the model, and 2) use the model with the GA to find those special combinations (among the vast number possible) that produce the kind of product your boss or client wants. Your boss thinks you’re a genius. You charge your client thousands to solve the problem and your client thinks he got the work done cheaply. Your cost, exclusive of your time – $995!
The AI Trilogy will be packaged with documentation and examples for distribution for new users sometime later this year. In the mean time, if any existing users want to purchase in advance, we’ll supply the components if purchased together for $995.
********************************************************
II. Clarification of www.ward.net
Many of our users, especially the new ones, are not really aware that www.ward.net is a web site separate from our sales web sites (www.wardsystems.com and www.neuroshell.com). We think some of you have been looking on wardsystems.com for our advanced tips and techniques and our new User Discussion Forum. If you haven’t checked out www.ward.net, please do so, especially if you feel you need deeper knowledge about our products.
*********************************************************
III. User Discussion Forum
The User Discussion Forum we announced in the last newsletter is now up and running on www.ward.net. Here is your chance to get ideas from your fellow users, instead of just the Ward Systems staff. Of course, we will be answering questions here too, but we will try to give our users a chance to answer queries first. We’d like to see you there!
*******************************************************
IV. Trader Tips. Did You Know…
Did you know that the NeuroShell Trader does standard linear regression? In fact there are two ways you can do linear regression. All versions of the Trader have a moving window linear regression in the Indicator category called “Regression”. However, in the Professional Versions, the Prediction Wizard does linear regression, too. Just set the number of hidden neurons to zero (see the Advanced tab in the Change Training Criteria button of the Wizard). Then your neural net is linear regression instead of a non-linear network! (Note to NeuroShell Predictor owners: you can set hidden neurons to zero also to get linear regression.)
Did you know that the Trader Professional and DayTrader Professional optimizers will automatically look at how your optimization is going on the out of sample evaluation period and seek to improve it? Many of you have asked for that, because you are doing it by hand. You are optimizing and noticing less than stellar results on the out-of-sample, so you change something and re-optimize. Read the Major Modeling Concern tip on www.ward.net for details.
********************************************************
V. Sports Prediction Using NeuroShell Predictor or Classifier
If you own the NeuroShell Predictor or Classifier, we think it would be taking unfair advantage of your colleagues for you to use them for betting in the office sports pools. After all, your colleagues do not have artificial intelligence prediction software. The fair places to use this software are Las Vegas, Atlantic City, and Monte-Carlo. But if you’re going to do it, you may as well know how. We have just modified our Sports Betting Tip on www.ward.net. Log in with your Predictor or Classifier Serial Number and read it. And remember that in many countries you must declare your gambling winnings to the tax authorities!