Professional Documents
Culture Documents
PROTOTYPING ML PAPERS
ELLEN KÖNIG / @ELLEN_KOENIG
• „Somebody must
have solved this
before!“
• Noready-to-use
implementation
A WORKFLOW FOR
PROTOTYPING ML PAPERS
3. Evaluate your
papers
4. Prioritize 5. Prototype
approaches approaches
STEP 1: SEARCH FOR RESEARCH
FINDINGS
Needed:
An overview of the field
COMPILING AN OVERVIEW OF
THE FIELD
Compile
Summarize
common metrics
and baselines
Pick simple
Minimally required
metrics and
metric targets?
baselines
Journal / conference
Team experience?
quality?
STEP 3: EVALUATE YOUR
PAPERS — A CHECKLIST
3. Results
2. Methodology
2. Methodology
banking documents
✔ Abstract & Introduction
METHODOLOGY SECTION
✓Seems to be complete
Pre-processing steps described completely?
✓Accuracy
Metrics appropriate for the problem?
? Not yet
Improvement analyzed with suitable statistical tests? ✔ Results
✔ Methodology
X No statistical analysis, and reported
measurements are not comparable ✔ Abstract & Introduction
RESULTS SECTION
✔ Methodology
High
Impact
Quick Major
Wins Projects
High
Effort
Fill-in Thankless
Jobs Tasks
STEP 5: PROTOTYPE YOUR
CHOSEN APPROACHES
A FEW RECOMMENDATIONS
Understand all
Compile a glossary equations & code
Reference
Higher level sections of
language papers
A FEW MORE
RECOMMENDATIONS
Compile the
Verify under same conditions performance in a table
MORE RECOMMENDATIONS
http://codecapsule.com/2012/01/18/how-to-
implement-a-paper/
SUMMARY: WHEN SHOULD YOU
LOOK FOR RESEARCH PAPERS?
• „Somebody must
have solved this
before!“
• Noready-to-use
implementation
SUMMARY: A WORKFLOW FOR
PROTOTYPING ML PAPERS
• Slide 4: https://www.datasciencecentral.com/
profiles/blogs/140-machine-learning-formulas
• Slide 6: https://pixabay.com/de/bremer-
stadtmusikanten-skulptur-2444326/
IMAGE CREDITS
• Slide 9: thenounproject.com
• Slide 10
• https://pixabay.com/en/book-address-book-learning-
learn-1171564/
• https://en.wikipedia.org/wiki/Map#/media/
File:World_Map_1689.JPG
• Slide 13