[root] Log of /trunk/tmva/src/CrossEntropy.cxx

Revision 23334 - (view) (download) (as text) (annotate) - [select for diffs]
Modified Sat Apr 19 18:38:57 2008 UTC (6 years, 9 months ago) by brun
File length: 3174 byte(s)
Diff to previous 21630

From Joerg Stelzer:
The following list contains the changes since ROOT release 5.18/00

* Dataset preparation:
o Preselection: Preselection cuts now work on arrays. Previously used TEventlists (only event wise pass/fail) were replaced by TreeFormulas (sensitive to array position). Thanks to Arnaud Robert (LPNHE) for his contributions.
o Tree assignment to signal/background: Signal and background trees can now be assigned individually to training and test purposes. This is achieved by setting the third parameter of the Factory::AddSignalTree/AddBackgroundTree() methods to "Train" or "Test" (const string). The only restriction is that either none or all signal (background) trees need to be specified with that option. It is possible to mix the two modes, for instance one can assign individual training and test trees for signal, but not for background.
o Direct tree building: For increased flexibility, users can also directly input signal and background, training and test events to TMVA, instead of letting TMVA interpret user-given trees. Note that either one of the two approaches must be chosen (no mix). The syntax of the new calls is described in the macros/TMVAnalysis.C test macro. --> The User runs the event loop, copies for each event the input variables into a std:vector, and "adds" them to TMVA, using the dedicated calls: factory->AddSignalTrainingEvent( vars, signalWeight ); (and replacing "Signal" by "Background", and "Training" by "Test"). After the event loop, everything continues as in the standard method.
* Methods:
o Simulated Annealing in Cuts,FDA: Entirely new Simulated Annealing (SA) algorithm for global minimisation in presence of local minima (optionally used in cut optimisation (MethodCuts) and the Function Discriminant (MethodFDA)). The SA algorithm features two approaches, one starting at minimal temperature (ie, from within a local minimum), slowly increasing, and another one starting at high temperature, slowly decreasing into a minimum. Code developed and written by Kamil Bartlomiej Kraszewski, Maciej Kruk and Krzysztof Danielowski from IFJ and AGH/UJ, Krakow, Poland.
o Cuts: Added printouts, quoting the explicit cut application for given signal efficiency. In case of transformations of the input variables, the full expressions are given. Added warning to Fisher in case of variable normalisation.
o Cuts: Added physical limits to min/max cuts if smart option is used.
o BDT: removed hard-coded weight file name; now, paths and names of weight files are written as TObjStrings into ROOT target file, and retrieved for plotting; available weight files (corresponding to target used) can be chosen from pop-up GUI.
o BDT: Changes in handling negative weights in BDT algorithm. Events with negative weights now get their weight reduced (*= 1/boostweight) rather than increased (*= boostweight) as the other events do. Otherwise these events tend to receive increasingly stronger boosts, because their effects on the separation gain are as if background events were selected as signal and vice versa (hence the events tend to be "wanted" in signal nodes, but are boosted as if they were misclassified). In addition, the separation indices are protected against negative S or S+B returning 0.5 (no separation at all) in case that occurs.
o BDT: In addition there is a new BDT option to ignore events with negative event weights for the training. This option could be used as a cross check of a "worst case" solution for Monte Carlo samples with negative weights. Note that the results of the testing phase still include these events and are hence objective.
o BDT: Added randomised trees: similar to the "Random Forests" technique of Leo Breiman and Adele Cutler, it uses the "bagging" algorithm and bases the determination of the best node-split during the training on a random subset of variables only, which is individually chosen for each split.
o BDT: Move to TRandom2 for the "bagging" algorithm and throw random weights according to Poisson statistics. (This way the random weights are closer to a resampling with replacement algorithm.)
o TMlpANN: Extended options to TMultilayerPerceptron learning methods. Added example for reader application: TMVApplication.py
* GUI:
o Parallel Coordinates: New GUI button for Parallel Coordinate plotting.
* Application:
o Added Python example for reader application: TMVApplication.py
* Bug fixes:
o TMlpANN: fixed crash with ROOT>=5.17 when using large number of test events; also corrected bias in cross validation: before the test events were used, which led to an overestimated performance evaluation in case of a small number of degrees of freedom; separate now training tree in two parts for training and validation with configurable ValidationFraction
o Cuts: Corrected inconsistency in MethodCuts: the signal efficiency written out into the weight file does not correspond to the center of the bin within which the background rejection is maximised (as before) but to the lower left edge of it. This is because the cut optimisation algorithm determines the best background rejection for all signal efficiencies belonging into a bin. Since the best background rejection is in general obtained for the lowest possible signal efficiency, the reference signal efficiency is the lowest value in the bin.
o Cuts: Fixed Cuts (optimisaton) method -> event with smallest value was not included in search for optimal cut (thanks to Dimitris Varouchas, LAL-Orsay, for helping us detecting the problem).
o Genetic Algorithm: Corrected configurable random seed in GeneticAlgorithm (thanks to David Gonzalez Maline, CERN, for pointing this out)
o GUI: Fixes in input-variable and MVA plotting: under/over-flow numbers given on plots were not properly normalised; the maximum histogram ranges have been increased to avoid cut-offs. Thanks to Andreas Wenger, Zuerich, for pointing these out.

This form allows you to request diffs between any two revisions of this file. For each of the two "sides" of the diff, enter a numeric revision.

Links to HEAD:	(view) (download) (as text) (annotate)
Sticky Revision:

	Diffs between and
	Type of Diff should be a