Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
G
GUM-compliant neural network robustness verification - a Masters thesis
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Model registry
Analyze
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
ludwig10_masters_thesis
GUM-compliant neural network robustness verification - a Masters thesis
Graph
152fbc292389fce2644734b95390ca3e849c8794
Select Git revision
Branches
1
main
default
1 result
You can move around the graph by using the arrow keys.
Begin with the selected commit
Created with Raphaël 2.2.0
1
Jan
31
Dec
28
27
13
12
4
30
Nov
29
27
24
23
22
18
17
16
14
13
12
10
9
8
7
6
5
31
Oct
29
23
19
18
17
14
13
12
11
10
9
7
8
Sep
30
Jul
24
27
Jun
26
18
16
15
24
May
1
12
Dec
6
29
Nov
15
3
Jul
2
25
Jun
feat(thesis): finish draft for objective section
feat(thesis): finish draft for motivation section
feat(thesis bib): extend references with another bunch of important publications and remove notes to avoid overfull hboxes
feat(thesis bib): extend references with a bunch of use cases and fundamental publications
feat(thesis): introduce algorithm
feat(thesis): refine unrobust definition
feat(thesis Makefile): introduce thm file
refactor(thesis): reformat code and correct whitespaces with that
refactor(thesis): improve formatting and comprehensibility of QuadLU proof
refactor(thesis): remove parametric from softplus where it is not needed
refactor(thesis): introduce a bunch of non-breaking spaces in the proof about sigmas differentiability
refactor(thesis): introduce hint about what is done in the LPU section as Sascha suggested
refactor(thesis): introduce short title for LPU section
feat(thesis): introduce title to proof for main LPU as there is a remark in between the theorem and the proof
refactor(thesis): introduce some more non-breaking spaces and capitalize Definition references and such
feat(thesis): introduce titles for all theorems and propositions
refactor(thesis): change requirement to prerequisite when talking about continuous differentiability
fix(thesis): improve and correct remark about continuous differentiability prerequisite
fix(thesis): correct matrix elements in symbols to lower case letter
fix(thesis): remove misleading and wrong uncertainty definition from symbols
feat(thesis): introduce open set Omega into symbols
refactor(thesis): change U as an open set to Omega not to confuse it with covariance matrices
refactor(thesis): remove one of Sascha's remarks as the definitions and references to the GUM are in place now
refactor(thesis): introduce short page header title for LPU for DNN
refactor(thesis): remove multivariate setting from GUM's definition of expanded measurement uncertainty
refactor(thesis): remove symbols from GUM definitions where they are not given in the GUM
refactor(thesis): remove one of the remarkboxes that is not needed anymore after merging preliminaries in other sections
refactor(thesis): correct capitalization
refactor(thesis): introduce one better space in formula
refactor(thesis): change element or coordinate to component when talking about vectors
refactor(thesis): improve formulation about the composition being applied element-wise
refactor(thesis): introduce two more non-breaking spaces
fix(thesis): improve definition of i^{(i)}
refactor(thesis): update one reference after doing a data_validation with biber and updating the bib
refactor(thesis references): update bib after doing a data_validation with biber
refactor(thesis): remove remarks on GUM section 4.3.7 about upper and lower bounds for uncertainties
refactor(thesis): introduce parametric when talking about quadlu
refactor(thesis): introduce non-breaking spaces all over
refactor(thesis): correct one formulation as Sascha suggested
refactor(thesis): introduce parameter into quadlu operator
Loading