Free cookie consent management tool by TermsFeed Policy Generator

Timeline


and

02/14/13:

16:18 Documentation/Howto/OptimizeAnyLogicModels edited by abeham
updated tutorial with changes made in integer-vector bounds (diff)

02/11/13:

10:15 Changeset [9215] by fschoepp

#1888:

  • Janitor is now working as expected in Windows Azure
  • Added basic support for experiments (draggable experiments)
  • Added methods to save/read experiments from TableStorage
  • The job status can now be retrieved by using the GetTasks/GetTaskData methods
  • Added a class to convert JSON-objects to Algorithm instances
  • Web page: Added experiment button to navigation

02/08/13:

23:16 Changeset [9214] by gkronber

#1967: added a benchmark function

21:57 Changeset [9213] by gkronber

#1508: changed the ranges for buy/hold/sell signals (1/3, 1/3, 1/3)

21:56 Changeset [9212] by gkronber

#1967: worked on Gaussian Process evolution problem

21:54 Changeset [9211] by gkronber

#1902 reformulated calculation of periodic covariance function

14:17 Changeset [9210] by ascheibe

#1886 added view for displaying result correlations

02/06/13:

13:45 Changeset [9209] by mkommend

#1890: Corrected copy & paste error in SymbolicRegressionConstantOptimizationEvaluator.

12:30 Changeset [9208] by sforsten

#1941:

  • added wisconsin breast cancer problem instance
  • corrected iris dataset
  • changed classification data descriptors to be able to set training and test partition as well as input and target variables (in the same way as it is done in regression)

02/05/13:

21:22 Changeset [9207] by ascheibe

#1890 disabled parallel task uploading as this produces a lot of failed db transactions and aborted uploads and therefore does not speed up uploading

13:04 Changeset [9206] by sforsten

#1980: branch project Problems.DataAnalysis

02/04/13:

16:26 Changeset [9205] by sforsten

#1980: forgot to remove the reference to any specific encodings in the LearningClassifierSystems project

16:16 Changeset [9204] by sforsten

#1980:

  • deleted not needed interface IMatching
  • finished VariableVector encoding
  • the algorithm LearningClassifierSystem is now independent of a specific encoding. It still needs the ConditionActionEncoding.
  • merged r9191:9203 HeuristicLab.Core from trunk to branch
15:56 StatisticalAnalysis edited by abeham
(diff)
15:07 Changeset [9203] by abeham

#2012:

  • Removed plugin HeuristicLab.SharpDevelop-3.1.1.5327
  • Added plugin HeuristicLab.SharpDevelop-3.2.1
    • Contains custom built binaries from SharpDevelop's 3.x branch
  • Changed dependency in HeuristicLab.CodeEditor-3.3
  • Removed log4net from ExtLibs
14:59 Ticket #2012 (Remove log4net dependency from SharpDevelop) created by abeham
SharpDevelop's ICSharpCode.SharpDevelop.Dom provides a LoggerService …
13:21 StatisticalAnalysis edited by abeham
H0 (diff)
13:10 StatisticalAnalysis edited by gkronber
Significant ;) (diff)
13:08 significant.png attached to StatisticalAnalysis by gkronber

02/03/13:

16:17 Changeset [9202] by ascheibe

#2005

  • add repeating of failed tasks and task datas
  • added an additional ws method that loads lightweight tasks without the statelogs
16:02 Changeset [9201] by ascheibe

#2005 merged changes from trunk into branch

02/01/13:

10:45 StatisticalAnalysis edited by abeham
(diff)

01/31/13:

22:24 Changeset [9200] by abeham

#1961: Fixed serialization of paused algorithm

22:17 Changeset [9199] by abeham

#1961:

  • Switched to ALGLIB's high quality normal distributed random number generator
  • Added automatic restriction to bounds after mutation in case MaxTries > 1 and no valid solution could be obtained
14:59 StatisticalAnalysis edited by ascheibe
(diff)
14:39 Changeset [9198] by ascheibe

#1886 added calculation of the overall parameter influence

13:13 Changeset [9197] by ascheibe

#1886 don't do testing if there aren't enough groups

11:03 Changeset [9196] by ascheibe

#1886

  • fixed a cloning bug
  • fixed forgotten event handler deregistration
  • added a run collection view for analyzing parameter influences
10:54 Ticket #2011 (GeneticAlgorithm's way of wiring the population size is not optimal ...) created by mkommend
This is severe malfunction, because if one changes the population size …
Note: See TracTimeline for information about the timeline view.