| |
| Download KnowledgeMiner®
Perplexity is the beginning of knowledge. - Khalil Gibran |
| (yX) for Excel and KnowledgeMiner |
KnowledgeMiner |
Download  |
Download  |
System requirements
Mac OS X 10.5 or newer
Microsoft Excel 2004 or 2008
Performance gains
On intel macs it runs parallel,
on ppc serially.
Takes full advantage of multi-core processors
64/32 bit universial binary.
64 bit is the default when downloded.
|
System
requirements
MacOS 10.2 or newer
Universal Binary (Intel or PPC) (G3/350 MHz or
better recommended)
64 MB RAM (256+ MB recommended) |
|
> Click here to read what's new in(yX) for Excel and KnowledgeMiner
| KnowledgeMiner (yX) for Excel
|
For
prices, click here.
Excel versions
|
SONAN
(max. inputs)
|
Similar pattern search
|
Model export to Excel
|
Diagram
generation
|
Data Sheet
rows / cols.
|
eBook
|
|
2004/ 2008
|
Yes (50,000)
|
Time process prediction
|
Yes
|
Yes
|
according to Excel version
|
Free
|
|
Common modeling technologies and their applicability
to different data set dimensions.
|
Edition
|
SONAN
(max. inputs)
|
Similar pattern search
|
FRI
|
2nd level
validation
|
Data Sheet
rows / cols.
|
eBook
|
|
Platinum
|
Yes (500) / Ex
|
P, C, Cl
|
Yes / Ex
|
Yes
|
30,000 / 30,000
|
Free
|
|
Demo*
|
Yes (50)
|
P, C, Cl
|
Yes
|
Limited
|
3,000 / 100
|
-
|
|
|
SONAN - Self-organizing Networks of Active Neurons (based on GMDH)
(Ex: supports use of dedicated exogenous and endogenous variables when building systems of equations)
Similar pattern search - Analog Complexing (AC) pattern recognition technology (P: prediction; C: clustering; Cl: classification)
FRI - Self-organizing Fuzzy Rule Induction technology
Validation - Second level, noise level adjusted evaluation of SONAN models to measure their reliability and descriptive power (more...)
eBook - Self-Organising
Data Mining (PDF file)
* Demo cannot save and print; SONAN and Fuzzy are limited
to 3 layers; AC is limited to a pattern length of 10
and a data length of 500
|
- spreadsheet like handling of data including simple
formulas and cell references
- several built-in mathematical functions for extending
the data basis
- opens ASCII text files
- creates automatically
- linear or nonlinear static regression models by Self-organizing Networks of Active Neurons (SONAN)
- multi-input/single-output models as well as multi-input/multi-output
models (system of equations) available analytically
and graphically
- linear or nonlinear dynamic regression models by SONAN
- 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
- enables background modeling
- Receiver Operator Characteristic (ROC)
for evaluation of the classification power of generated
models
- stores all created models in a model base dynamically
- all models can be used for status-quo or what-if predictions,
classification or diagnosis problems within KnowledgeMiner
- copy (PDF file) of the book by Mueller/Lemke "Self-Organising
Data Mining"
- AppleScript support for program-to-program communication, task automation, and knowledge discovery workflow across the system or a network (not available
on Windows systems). Read the book AppleScript for Absolute Starters by Bert Altenburg. It is free (PDF, 896k).
- creates nonparametric prediction models for fuzzy objects
by Analog Complexing, an advanced pattern recognition
technology for evolutionary processes. A synthesis of different
prediction models (SONAN-based and Analog Complexing-based)
is now possible as a powerful way to increase prediction
accuracy.
- provides Fuzzy Rule Induction as a third self-organizing
data mining method for modeling, classification and prediction
tasks
- for the first time, integrated noise filtering characteristics for a second level, on-the-fly model validation; supports evaluation if a model reflects a causal relationship or if it just models noise
- two new data mining algorithms: Analog Complexing based clustering and classification (n classes)
- explicit definition of exogenous and endogenous variables for creation of systems of equations and their what-if type prediction
- TransformModel for implementing models in Microsoft Excel
| Unique Features of KnowledgeMiner |
- Self-organizing Networks of Active Neurons that perform
- Active Neurons selecting their input variables themselves
- advanced network synthesis and model validation techniques
to end up in a robust, optimal complex model
- integrated two stage model validation
- 1. level: leave-one-out cross-validation driven model synthesis to avoid overfitted models (noise filtering)
- 2. level: noise filtering characteristic of the first stage is applied to the final model to check if it really reflects some causal relationship (model evaluation)
- creation of a best and autonomous system of equations
(a network of Self-organizing Networks of Active Neurons) that is ready for long-term status-quo and what-if predictions of the complete system; every system is available analytically (equations or rules) and graphically (system graph of the interdependence structure)
for results interpretation
- Analog Complexing as a powerful pattern search
technology to create cluster, classifications, or predictions for fuzzy processes (the
most market processes e.g.) which other methods may be not
appropriate for.
- Fuzzy Rule Induction from data to describe objects
in a more natural language qualitatively
- explanatory power of any created model by default
- a model base to store all models and to keep connected
information together
- completely autonomous modeling process that can work as
background process on your computer saving your resources
either by working simultaneously with the modeling process
or, for larger problems, by running the process overnight
- allows for knowledge discovery workflow processing via AppleScript (Mac only)
|
|
|