KnowledgeMiner shows how quick and easy it should be to produce powerful models and predictions for complex systems. We believe it will help you get your work done better and faster. Why? Because KnowledgeMiner is a unique and different kind of statistical modeling program that uses methods not found in any other modeling tool. A more detailed description is available on our web site which has also been included in the info folder of this package.
This version of KnowledgeMiner is complete and fully functional in every way except for the following limitations:
Ñ You cannot save a file.
Ñ You cannot print a file. (if you find this limiting in any way email and let us know)
After registering the program you will receive the unlock code that allows you to save and print. Registration is easily done by email or phone. If you have any questions at any time please email or call us. Your feedback is essential to making a better product since we want to satisfy everyones needs for a great statistical modeling and prediction program.
KnowledgeMiner comes with an AppleGuide based Tutorial which will assist you in creating your first models and making predictions with them. If you want to use this Tutorial (we recommend it) you need to have AppleGuide and QuickTime installed on your machine. To start working with KnowledgeMiner open the document COD concentration* located in the Examples folder and choose KnowledgeMiner Tutorial in the Help menu (the help menu is the ? at the very right side and top of the screen in the menubar, this opens the appleguide for KnowledgeMiner). After you finish the tutorial please try out the various demonstrations of the power of KnowledgeMiner included in the examples folder.
IMPORTANT: One window at a time can be opened to open a new example first close the open window.
We hope to add more information, examples and documentation over time to this shareware version of KnowledgeMiner.
KnowledgeMiner Lite -- Price $100 or $45 for students
Ñ the first implementation of advanced, easy-to-use Statistical Learning
Network algorithms - called Group Method of Data Handling (GMDH). It
combines the best of both statistics and Neural Networks to a new modeling
category extracting hidden knowledge in data. Models are represented in
form of networks of active neurons which are available analytically
immediately after modeling. This means, you don't have to guess why results
are as they are.
Ñ spreasheet like handling of data including simple formulas and cell references
Ñ several built-in mathematical functions for extending the data basis:
x^y, x^(y/z), trigonometric, exponential and logarithmic functions, mean, sum
and standard deviation, correlation analysis, random values, add uniform noise;
Ñ opens ASCII text files;
Ñ creates automatically linear or nonlinear static GMDH-models
Ñ multi-input/single-output models as well as multi-input/multi-output
models (system of equations) available analytically and graphically
linear or nonlinear dynamic GMDH-models
Ñ time series models, multi-input/single-output models as well as
multi-input/multi-output models (predictable system of equations)
available analytically and graphically for up to
Ñ 50 input variables
Ñ enables background modeling;
Ñ stores all created models in a model base dynamically;
Ñ all models can be used for status-quo or what-if predictions, classification or diagnosis problems within KnowledgeMiner;
KnowledgeMiner Professional -- Price $380
KnowledgeMiner Pro is the modeling and prediction tool needed to deal with complex, real-world problems for prediction, classification or diagnosis. It provides in addition to KnowledgeMiner Lite these features:
Ñ creates GMDH-models automatically for up to
Ñ 500 input variables enabling solution of complex real-world time
processes and modeling tasks. More variables then 500 inputs are
possible, if this is something you need please call us to discuss custom
programming;
Ñ it is possible to use a third data set, the examination set, additionally to
training and checking sets for model performance validation during
modeling. The validation results have influence on the selection and the
network synthesis process.
Ñ creates nonparametric prediction models for fuzzy objects by Analog
Complexing, an advanced pattern search technology for evolutionary
processes. A synthesis of different prediction models (GMDH-based and
Analog Complexing-based) is now possible as a powerful way to increase
prediction accuracy.
Ñ has more convenient features to deal with large modeling problems.
Unique Features of KnowledgeMiner
Ñ GMDH-type Neural Networks that perform
Ñ Active Neurons select their input variables themselves;
Ñ advanced network synthesis and model validation techniques ensure a
robust, optimally complex model;
Ñ creation of a best and autonomous system of equations (network of GMDH-
type Neural Networks) which is ready for status-quo predictions of the
complete system by default and which is available analytically and graphically
(system graph) for results interpretation;
Ñ a model base to store all models and to keep connected information together;
Ñ Analog Complexing as a powerful pattern search technology to create
predictions for fuzzy processes (the most market processes e.g.) which other
methods may be not appropriate for.
Ñ completely autonomous modeling process which can work as background
process on computers saving your resources either by working simultaneously
with the modeling process or, for larger problems, by running overnight.
NOTE: If you need a version that take advantage of the floating-point math coprocessor, please call. There is no extra cost. Also we can produce custom versions to suit your needs.
Shareware
Please Support Mac Shareware
We hope you like KnowledgeMiner. To purchase KnowledgeMiner please use the registration form that came with KnowledgeMiner. Payment can be by credit card and sent via email or by check, cash or money order and sent by mail or you can call in your order.
Pricing (includes free upgrades)
KnowledgeMiner Lite is $100 or $45 for students
KnowledgeMiner Professional is $380 or
Upgrade from the Lite to the Pro version for $300
Custom versions please call
Please direct any questions to julian@sierra.net or (916) 546-9005
Registered users receive:
Ñ A key to unlock the program so it can save and print.
Ñ The knowledge that you are participating in the evolution of KnowledgeMiner
Ñ All future upgrades and enhancements are available free to registered users
Ñ E-mail hotline tech support
Ñ Email notifying you immediately of new versions
Ñ Registered users can recommend new features and contribute to the direction of KnowledgeMiner
Ñ Access to all features.
Ordering
Use the included registration form to order or call (916)546-9005
Description of other Products -
iView, iSearch, iCount, CopyPaste, KnowledgeMiner
╩
iSearch - finds text any where on disk. Fast and easy to use. iSearch adds to and updates the Macs find file. Can solve the problem of where some text is and works in the background. Use TextSearch to search for text in files on any mounted volume. Subsequently select thefound files and: (a) Get info from the finder about the files; (b) Open the file parent folder; (b) Launch the file with the associated application.
╩
iCount - jumps way beyond that old Mac calculator with a variable size calculator that can perform regular, scientific or statistical functions. Multi-function desktop calculator, expression parser. Unlike any other desktop calculators, iCount doesn't emulate a normal hand calculator. Instead it has a simple editor that lets the user type an expression and returns the result simply by pressing the return key. iCount supports: drag and drop text editing; 4 modes of operation; 27 built-in functions and up to 50 user defined functions; on-line help and much more.
╩
CopyPaste - is the award winning clipboard utility that adds 10 clipboards to your Mac. CopyPaste also does application switching, text, picture and date processing, clipboard archives and much more. CopyPaste is essential to writers, editors, desktop publishers and anyone who copies and pastes.
╩
KnowledgeMiner! - is an inductive learning modeling and prediction tool which enables you to quickly open up new possibilities in your daily work using its revolutionary modeling features. It is an Artificial Intelligence tool to extract hidden knowledge from data and which is basically build on the cybernetic principals of self-organization: learning a completely unknown relationship between outputs and inputs of any given system in an evolutionary way from a very simple organization to an optimally complex one. The main advantages of this inductive approach are:
Ñ Only minimal, uncertain a priori information about the system is required. That means, even if you have no experience in modeling, data analysis or designing a neural network you will be able to model, analyse and predict very complex relationships of nearly any kind of system.
Ñ It features a very fast and effective learning process which works quickly on any Mac. That means, you can solve problems on your desktop which previously required a workstation and extremely expensive software.
Ñ Modeling on very short and noisy data samples (6+). That means, you can deal with a problem as is and don't have to construct artificial conditions for your modeling method to get it work.
Ñ Output of an optimal complex and cross-validated model. That means, you generally can be sure to get a model at the end of the automated modeling process which could be expected not to be overfitted. Overfitted models are not able to predict the inherent relationship between variables.
Ñ Output of an analytical model as a transparent explanation component. That means, you can evaluate the analytical model to explain the obtained results immediately after modeling.
KnowledgeMiner! works on advanced inductive learning modeling algorithms - known as Group Method of Data Handling (GMDH) as a representative of statistical learning networks - on which you can create time series models, input-output models and predictable systems of equations in one document. It is possible, for example, to create a linear or nonlinear system of equations for 30 output and 250 input variables using only 25 observations for each variable automatically.
The power and the advantages of SelfOrganize! in comparision with statistical modeling tools as well as with neural networks modeling tools make it easy and fast applicable on a wide range of real-world problems and to one of the most effective modeling and prediction tool available.
If some of the above makes sense to you then you'll enjoy KnowledgeMiner if you don't understand it then checking it out will certainly give you an education. ;-)
Thanks for Supporting Mac Software
The Latest Versions of
* KnowledgeMiner * iView * iSearch * iCount * CopyPaste * are located here:
http://www.scriptsoftware.com
For more information, questions or feedback contact:
Frank Lemke or Julian Miller
Bergener Strasse 1 PO Box 854
D-10439 Berlin Crystal Bay, NV 89402
Germany USA
Frank_Lemke@magicvillage.de julian@sierra.net
Thanks for Supporting Mac Shareware!
*Data Source: Self-Organizing Methods in Modeling: GMDH Type Algorithms, Marcel-Dekker, Inc., New York 1984
