home *** CD-ROM | disk | FTP | other *** search
Text File | 1999-03-22 | 2.7 KB | 72 lines | [TEXT/ttxt] |
- KnowledgeMiner History
-
-
- March/23/1999 - version 3.0
-
- Ñ New modeling method: Self-organizing Fuzzy Rule Induction (Fuzzy-GMDH)
- Ñ available for the first time on any personal computer
- Ñ combines modeling of fuzzy objects with natural language-like interpretational power of the generated models
- Ñ larger and now customizable data sheet (up to 10,000 rows/ 200 columns)
- Ñ improved GMDH by information matrix optimization
- Ñ improved and updated Help menu (AppleGuide, Balloons)
- Ñ updated and extended examples collection
- Ñ fixed bug that may occur when reading ASCII text files
- Ñ scaled into Copper, Silver and Gold editions
-
-
-
- June/28/1998 - version 2.2.3
-
- Ñ first PPC only version
- Ñ improved Analog Complexing method
- Ñ several bugs are fixed making the program more stable under low memory conditions
- Ñ redesigned "Modeling" and "Window" menus
-
-
-
- February/4/1998 - version 2.2.2
-
- Ñ fixed bug that may occur when reading large files
- Ñ new features will not be supported for the 68k based version beginning from this version
-
-
-
- December/15/1997 - version 2.2.1
-
- Ñ 32k ASCII text import limit removed
- Ñ fixed bug that causes a crash when calculating a large number of formulas in spreadsheet
- Ñ fixed bug on PowerMac that does a wrong cell assignment when verifying a spreadsheet input by mouse click
- Ñ improved and updated the text files and apple guide
-
-
-
- October/24/1997 - version 2.1
-
- Ñ tutorial updated - new context check features
- Ñ removed bug that allowed opening two documents at once on PowerMac
-
-
-
- October/1/1997 - version 2.0
-
- Ñ optimized for PPC and 68kFPU based Macs
- Ñ PPC native app runs 8-10 times faster than 68k based version. Now it is possible to mine very large data sets for
- relevant relations or patterns within minutes instead of days.
- Ñ Analog Complexing
- Ñ available for the first time on a personal computer (Mac) as shareware.
- Ñ shows automatically a prediction interval graphically (the calculated possible upper and lower limits) along with
- the most likely prediction of points. Now a prediction consists not only of sharp points but reflects also the
- inherent fuzziness and uncertainty of the objects. Applied to financial time series forecasting, e.g., this view
- focuses on the demand to consider the volatility of assets to get more reliable forecasts and decisions.
- Ñ optimized modeling algorithms to make self-organization of structures and knowledge extraction from data far
- more effective than neural networks or statistics
- Ñ Lite version
- Ñ now has a larger table to work with data
- Ñ two levels to setup modeling
- Ñ a standard and
- Ñ an advanced modeling setup dialog
-
-
- May/1/1997 - initial release
-
-