Press Release

 

Thursday, May 1, 1997

 

KnowledgeMiner 1.0 Now Available

(This software only available on the Macintosh platform)

 

KnowledgeMiner can be downloaded free from this location

http://members.aol.com/selforg/index.html

 

May 1st a revolutionary shareware tool for the Macintosh

arrives in the form of KnowledgeMiner. KnowledgeMiner was

created by an international team of experts in the areas of

cybernetics, statistical modeling, mathematics and computer

science. Now more then ever better software tools are needed

to mine the mountains of information that are accumulating

in the world and available on the internet. KnowledgeMiner

transcends both neural nets (NN) a part of artificial

intelligence (AI) and traditional statistics using new

techniques and based on GMDH modeling theory that has

already been very successful in decision support in economy

(analysis and prediction of economical systems, stock

market, sales and financial predictions, balance sheet

prediction), ecology (analysis and prediction of ecological

processes like air and soil temperature, air and water

pollution, drainage flow, Cl- and NO3-settlement, influence

of natural position factors on harvest, growth of wheat),

and health (diagnosis of cancer in complex cases). The

above examples come with the free downloadable version of

KnowledgeMiner. Self-Organized modeling is quite new and

KnowledgeMiner is the first and only software tool of this

type. Professionals in many areas can benefit by

downloading this tool and using it to mine in their field to

tap new discoveries.

 

KnowledgeMiner is based on the insights of the revered

Ukrainian cyberneticist, A.G.Ivakhnenko, who was discouraged

by the fact that many types of mathematical models require

the modeler to know things about the system that are

generally impossible to find. In fisheries modeling, for

example, the modeler may be required to know the migration

patterns of certain species of fish, or the fertility levels

of certain age groups. If modelers are forced to make wild

guesses at these variables, they can hardly expect to

produce a model with a great deal of reliability as to

prediction.

 

Past efforts of using the known tools of artificial

intelligence were not, in many cases, successful. That is,

because previous methods of artificial intelligence and

statistics are based on knowledge extraction using

subjective and creative human skills for model building

(called the knowledge engineering bottleneck).

 

Today experience has shown that there is a need for highly

structured models to stop putting users prejudicies into

models and to minimize their involvement in the overall

knowledge extraction process by making it more automated and

more objective: in other words, creating models that permits

inclusion of valid a priori knowledge and then looking only

at the data and nowhere else.

 

Frank Lemke and a team of researchers inspired by the

theories of Prof. Ivaknenko developed KnowledgeMiner which

realizes an advanced GMDH algorithm as well as the Analog

Complexing method for modeling and prediction of complex

systems. Frank Lemke has written many papers and is a

recognized expert in GMDH and has specialized in

self-organized modeling based solutions and information

systems for over 5 years. He choose the Macintosh because

of its ease of use, power, and success in the areas of science,

biotechnology, engineering, and education.

 

KnowledgeMiner is a powerful, easy-to-use modeling and

prediction tool which was designed to support the knowledge

extraction process from data on a highly automated level. It

works using two advanced self-organizing modeling

technologies: Group Method of Data Handling (GMDH) and

Analog Complexing. Other, complementary self-organizing

modeling methods are recently in development. Built on the

cybernetic principles of self-organization, KnowledgeMiner

brings high-end modeling capabilities on your desktop

without the need of being an expert in modeling since it

will learn completely unknown relationships between outputs

and inputs of any given system in an evolutionary way from a

very simple organization to an optimal complex one by

itself.

 

The main advantages of this inductive approach are:

 

Only minimal, uncertain a priori information about the

system is required. That means, even if you are not an

expert in modeling, data analysis or designing a neural

network you will be able to model, analyse and predict very

complex objects of nearly any kind of system.

 

A very fast and effective learning process is possible

on any Mac. That means, you can solve problems on your

desktop in a reasonable time which you may never have been

possible before.

 

Modeling on very short and noisy data samples. That means,

you can deal with a problem as it is and don't need to

construct artificial conditions for your modeling method to

make it work.

 

Output of an optimal complex and cross-validated model. That

means, you commonly can expect to get a model which is

robust, as simple as possible and not overfitted. Overfitted

models are not able to predict variables due to their

reflection of random relationships between variables.

 

Output of an analytical model as a explanation component.

That means, you can evaluate the analytical model to

interpret the obtained results immediately after modeling.

You don't have to guess why results are as they are.

 

In KnowledgeMiner you deal with data in spreadsheets and,

through its built in model base, you are able to create and

store time series models, input-output models and

predictable systems of equations (networks of input-output

models) for each variable in one document. These models are

applicable to sets of new data (prediction, classification,

diagnosis) within KnowledgeMiner immediately. There is no

need to import them as C code into other applications or to

do other efforts to get them to run.

 

KnowledgeMiner not only does useful work for you

automatically but also gives you the freedom to get some

other work done at the same time by sending the complete

knowledge extraction process to operate in the background on

your computer.

 

The power and the advantages of KnowledgeMiner in

comparision with statistical modeling tools and neural

networks make it stand out as easier, faster and more

applicable to a wide range of real-world problems. This

makes KnowledgeMiner the least expensive and most effective

modeling and prediction tool available on any platform.

 

>Availabile on May 1st. The revolution begins!

KnowledgeMiner and more information will be available for

download from

http://members.aol.com/selforg/index.html

Published papers, resumes and examples described above will

also be available on that site. Two other more powerful

versions of KnowledgeMiner will also be made available and

can be purchased directly from Script Software.

For more information email or call us at

Contact Email Telephone

Julian Miller julian@sierra.net (916)546-9005

Frank Lemke Frank_Lemke@magicvillage.de +4930 4443585

 

Hardware Requirements 68020 Mac, PowerMac or higher, MacOS

7.0 or newer, 8+MB RAM, Hard Disk, AppleGuide, and QuickTime

are recommended For KnowledgeMiner Pro a high-end

PowerMacintosh is recommended.

 

 

 

Back to the Top Script Software