issues
search
slds-lmu
/
paper_2019_iml_measures
Quantifying Interpretability of Arbitrary Machine Learning Models Through Functional Decomposition
https://arxiv.org/abs/1904.03867
15
stars
4
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Workshop
#14
christophM
closed
5 years ago
0
Discuss MEC and IAS for trees
#13
christophM
closed
5 years ago
0
Mention in discussion the usefulness of measures for white box models
#12
christophM
closed
5 years ago
0
Explain intuition behind the ALE Equation (2)
#11
christophM
closed
5 years ago
0
Check references
#10
christophM
closed
5 years ago
0
Use longer hyphen ("--" in LaTeX) for ranges (like 1 - 3)
#9
christophM
closed
5 years ago
0
Add variance measure to MEC
#8
christophM
closed
5 years ago
0
Add hyperparameter settings in column names of Table 2
#7
christophM
closed
5 years ago
0
application: Consider cut-off for models above certain MAE threshold
#6
christophM
closed
5 years ago
1
Reconsider breakpoint optimization
#5
christophM
closed
5 years ago
1
Explain the tuned hyperparameters (mtry, sigman, ...)
#4
christophM
closed
5 years ago
0
Describe why segmented regression was not used for MEC
#3
christophM
closed
5 years ago
0
Workshop
#2
christophM
closed
5 years ago
0
sorry for the commas
#1
giuseppec
closed
5 years ago
0