Opened 4 years ago
Last modified 2 years ago
#3075 accepted feature request
Implement symbolic regression problem instances from "AI Feynman" paper.
Reported by: | gkronber | Owned by: | chaider |
---|---|---|---|
Priority: | medium | Milestone: | HeuristicLab 3.3.17 |
Component: | Problems.DataAnalysis.Symbolic.Regression | Version: | trunk |
Keywords: | Cc: |
Attachments (1)
Change History (37)
Changed 4 years ago by gkronber
comment:1 Changed 4 years ago by gkronber
- Description modified (diff)
comment:2 Changed 4 years ago by chaider
comment:3 Changed 4 years ago by chaider
r17638 Added first part of feynman equations as instances
comment:4 Changed 4 years ago by chaider
- Added rest of part I equations
- Set Training/Test Partitions to 10^{5 }
comment:5 Changed 4 years ago by chaider
r17640 Added equations of part II
comment:6 Changed 4 years ago by chaider
r17641 Added part III of feynman equations
comment:7 Changed 4 years ago by chaider
r17642 Added field and constructor to define sample size in instances
comment:8 Changed 4 years ago by chaider
r17643 Added feynman bonus equations
comment:9 Changed 4 years ago by chaider
r17644 fixed exponent in Feynman II.6.15a
comment:10 Changed 4 years ago by chaider
- Updated instances (removed 2*pi term from equations)
- Added instances to InstanceProvider
comment:11 Changed 4 years ago by chaider
- Added possibility to add noise to the feynman instances
- Sorted instances by name
comment:12 Changed 4 years ago by chaider
r17649 Added noise instances for feynman bonus instances
comment:13 Changed 4 years ago by chaider
r17659 Fixed issues in some instances
comment:14 Changed 4 years ago by gkronber
- Milestone set to HeuristicLab 3.3.17
- Owner set to gkronber
- Status changed from new to accepted
comment:15 Changed 4 years ago by gkronber
- Version set to branch
comment:16 Changed 4 years ago by gkronber
- Status changed from accepted to reviewing
comment:17 Changed 4 years ago by gkronber
- r17670 Fix order of instances and add information on reference publication and description.
- r17671 Removed "Feynman" prefix from all instances
- r17672 rename file for reodering
- r17673 reorder instances
- r17674 small changes while reviewing
- r17675 reordering part1
- r17676 reorder part2
- r17677 update class names to match file names, split problem instances into 'small' and 'large' instances with separate providers
- r17678 changed title for noise part
comment:18 Changed 4 years ago by gkronber
- r17681: merged r17646:17648 from trunk to branch to prepare for reintegration
- r17682: merged r17638:17681 from branch into trunk
comment:19 Changed 4 years ago by gkronber
- Version changed from branch to trunk
comment:20 Changed 4 years ago by gkronber
r17683: deleted branch
comment:21 Changed 4 years ago by gkronber
r17684: include correct files in .csproj
comment:22 Changed 4 years ago by gkronber
The problem instances provider should not be the default selected one. Instead CSV should be the default. Right now AI is ordered first.
comment:23 Changed 3 years ago by gkronber
Discovered problem instance providers are ordered by Name in ProblemView line 70:
problemInstanceProviderComboBox.DataSource = ProblemInstanceProviders.OrderBy(x => x.Name).ToList();
comment:24 Changed 3 years ago by gkronber
r17804: start Name of CVS instance provider with a space to make sure it is ordered first.
comment:25 Changed 3 years ago by gkronber
- Use the same noise levels and calculation as in our experiments for the IEEE TeC paper.
- Reorder instances by name first and noise level second.
- Remove number of samples from the name.
comment:26 Changed 3 years ago by gkronber
- Owner changed from gkronber to mkommend
comment:27 Changed 3 years ago by mkommend
r17966: Changed Feynman problem instances to new normal distributed RNG.
comment:28 Changed 3 years ago by mkommend
r17967: Add GlobalSuppression file to HL.Problems.DataAnalysis.Instances to prevent persistence analyzer messages about missing StorableTypeAttributes.
comment:29 Changed 3 years ago by mkommend
r17969: Correct project file for HL.Problems.Instances.DataAnalysis.
comment:30 Changed 3 years ago by chaider
- Added target without noise to noisy instances
- Moved noise calculation to descriptor
comment:31 Changed 3 years ago by chaider
r17974 Fixed refactor issue for feynman1
comment:32 Changed 3 years ago by mkommend
- Owner changed from mkommend to chaider
- Status changed from reviewing to assigned
Check and adapt (if necessary) noise ratios of Feynman instances so that these are equivalent to the noise ratios of the Friedman problems.
If the different calculation has been introduced on purpose, we should define what we understand under noise ratio and how to calculate it.
comment:33 Changed 3 years ago by chaider
r18032 noise generation method to ValueGenerator; use same method for generating noise in friedman and feynman instances
comment:34 Changed 3 years ago by chaider
- Status changed from assigned to accepted
comment:35 Changed 2 years ago by gkronber
Noise generation introduced in r18032 does not work for noise ratio = 1 (which means no signal left)
comment:36 Changed 2 years ago by gkronber
r18106: changed noise levels for Feynman instances.
r17635 branched trunk