Published February 28, 2019
| Version v0.2.8
Software
Open
johannbrehmer/madminer: v0.2.8
- 1. Center for Data Science & Center for Cosmology and Particle Physics, NYU
- 2. UCI
- 3. New York University
- 4. CERN
Description
Breaking / API changes:
- The keyword
trainer
inMLForge.train()
has been renamed tooptimizer
- The gradient of network output wrt x is no longer calculated, the corresponding keywords in
MLForge.evaluate()
andMLForge.train()
are gone MLForge
has new methodsevaluate_log_likelihood()
,evaluate_log_likelihood_ratio()
, andevaluate_score()
;MLForge.evaluate()
just wraps around them now
- Fixed a number of bugs affecting neural density estimation methods ("NDE" and "SCANDAL")
- Fixed bugs when trying to use CASCAL
- Rewrote training procedure from scratch
- Some more refactoring of the ML parts
Files
johannbrehmer/madminer-v0.2.8.zip
Files
(16.8 MB)
Name | Size | Download all |
---|---|---|
md5:c899ea4c9207d7a6fd2ffe57191797d0
|
16.8 MB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/johannbrehmer/madminer/tree/v0.2.8 (URL)