SlideShare a Scribd company logo
1 of 37
Download to read offline
merantix.com Adrian Locher
Establishing the
future of AI in
Europe
Berlin AI Dr. Rasmus Rothe May 10, 2017
3 learnings from applying Deep Learning
to real world problems
Merantix GmbH, Berlin
HackZurich 2017: Sep 15 - 17, 2017
Quick reminder: Deep Learning
Neural networks in real world applications
Facebook face recognition Neural networks in autonomous driving
Companies working on deep learning
How we work at Merantix
Dataset
Ventures
Products
Machine Learning
3 learnings
It is actually more difficult than in theory...
First learning:
Value of pretraining
Problem: Datasets are expensive
Example 1 medical diagnostics: Cost for annotating 10’000 medical images
— 30min required per labelled image
— 100 EUR/hour
— 2 images/hour
— 50 EUR/image
EUR 500’000
Example 2 credit scoring: Cost of knowing if someone defaults
— To estimate default risk, labels of
defaulted people are required
— You can only get them if you let them
default
EUR 10’000/d
Assuming average default volume of EUR 10K
Pretraining is the solution!
Pretraining with cheap but large datasets on related domain1
Fine-tuning with well labeled data2
Performance
boost!!
How to get data for pretraining
IMDB
WIKI
25 36 14 51
66 34 54 18
Crawl dataPublic datasetsPretrained models
...
...
Weakly labeled data: Medical imaging
We don’t have labeled data so we get the labels from medical reports
We extract text
labels via NLP
and use them for
training
How do we do this?
1 Condition 2 Prognosis
Keine Pleuraerguss in der linken Lunge
Keine Erguss in der linken Lunge
Keine Pleuraergusses in der linken Lunge
Keine Randwinkelerguss in der rechte Lunge
Keine Erguß in der Lunge
Word embeddings
help to come up with
smart rules
If “Kein”/”Keine” → NO_EXISTENCE
If “Einige Beweise” → SMALLER_EXISTENCE
Else → DEFINITE_EXISTENCE
Second learning:
Caveats of real label distributions
Academic datasets are balanced
Example 1: MNIST - equally many samples per digit Example 2: Food 101 - perfectly balanced
... ... ... ... ... ... ... ... ......
TrainingsetTestset
... ... ... ... ... ... ... ... ......
Real world datasets are not...
Credit scoring Medical Imaging
1-2% of people default Luckily, the majority of people are healthy
And: Making mistakes can be expensive
Credit scoring Medical Imaging
AcceptReject
Paid Defaulted
$
$$$$$
Diagnosed
Not
diagnosed
Healthy Sick
How to cope with this
Sick
Sick
Sick
Be careful
Training Inference
Rare class A
Rare class B
Frequent class
Rare class A & B
Frequent class
1. More data
2. Change labeling
How to cope with this
Easy:
Hard:
Oversampling Undersampling Negative mining
Hard:
Training batch Weighting of loss
3. Sampling
4. Weighting
Third learning:
Understanding black box models
Neural networks are black boxes
Lin. regression / decision trees:
Decision mechanism can be easily explained
Neural networks:
Complex systems are hard to understand!
In reality: 100m+ parameters….
This is problematic in the real world! Why?
King penguin Starfish Baseball Electric guitar
+E =
Panda
57.7% confidence
Gibbon
99.3% confidence
Can the neural network be fooled? Does it really work in production?
This is problematic in the real world! Why?
Why DIDN’T it work? What biases does it learn?
Our Picasso Visualizer in practice
Partial occlusion Saliency map
Soon to be open-sourced!
Join us on our journey
Science1 Datasets2 Business3
Research on the bleeding edge of
deep learning.
Get access to some of the best
datasets in the world.
Grow businesses in the space of
AI/deep learning
WEBSITE CONTACT SOCIAL
merantix.com Twitter: @merantix
Github: merantix
Dr. Rasmus Rothe
rasmus@merantix.com

More Related Content

Similar to 3 learnings from applying Deep Learning to real world problems

Brief Tour of Machine Learning
Brief Tour of Machine LearningBrief Tour of Machine Learning
Brief Tour of Machine Learning
butest
 
Disasters and Humans (DEMS3706 SU2020, Dr. Eric Kennedy)APDEMS370
Disasters and Humans (DEMS3706 SU2020, Dr. Eric Kennedy)APDEMS370Disasters and Humans (DEMS3706 SU2020, Dr. Eric Kennedy)APDEMS370
Disasters and Humans (DEMS3706 SU2020, Dr. Eric Kennedy)APDEMS370
AlyciaGold776
 
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
Sri Ambati
 
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical ResearchII-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
Dr. Haxel Consult
 
Big Data Means Big Potential Challenges for Nurse Execs Response.pdf
Big Data Means Big Potential Challenges for Nurse Execs Response.pdfBig Data Means Big Potential Challenges for Nurse Execs Response.pdf
Big Data Means Big Potential Challenges for Nurse Execs Response.pdf
bkbk37
 

Similar to 3 learnings from applying Deep Learning to real world problems (20)

Predicting Diabetes Using Machine Learning
Predicting Diabetes Using Machine LearningPredicting Diabetes Using Machine Learning
Predicting Diabetes Using Machine Learning
 
30 Argumentative Essay Examples In Illustrator Go
30 Argumentative Essay Examples In Illustrator  Go30 Argumentative Essay Examples In Illustrator  Go
30 Argumentative Essay Examples In Illustrator Go
 
Brief Tour of Machine Learning
Brief Tour of Machine LearningBrief Tour of Machine Learning
Brief Tour of Machine Learning
 
Case Study: Advanced analytics in healthcare using unstructured data
Case Study: Advanced analytics in healthcare using unstructured dataCase Study: Advanced analytics in healthcare using unstructured data
Case Study: Advanced analytics in healthcare using unstructured data
 
Disasters and Humans (DEMS3706 SU2020, Dr. Eric Kennedy)APDEMS370
Disasters and Humans (DEMS3706 SU2020, Dr. Eric Kennedy)APDEMS370Disasters and Humans (DEMS3706 SU2020, Dr. Eric Kennedy)APDEMS370
Disasters and Humans (DEMS3706 SU2020, Dr. Eric Kennedy)APDEMS370
 
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
Explaining Black-Box Machine Learning Predictions - Sameer Singh, Assistant P...
 
"Gimme my damn data!" - e-Patient Dave's keynote at Medicine 2.0 2009
"Gimme my damn data!" - e-Patient Dave's keynote at Medicine 2.0 2009"Gimme my damn data!" - e-Patient Dave's keynote at Medicine 2.0 2009
"Gimme my damn data!" - e-Patient Dave's keynote at Medicine 2.0 2009
 
Introduction to Data Science
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data Science
 
Sunset Writing Paper Set, Optional Storage Box Pen
Sunset Writing Paper Set, Optional Storage Box PenSunset Writing Paper Set, Optional Storage Box Pen
Sunset Writing Paper Set, Optional Storage Box Pen
 
Artificial intelligence(chirag mittal)
Artificial intelligence(chirag mittal)Artificial intelligence(chirag mittal)
Artificial intelligence(chirag mittal)
 
Message mapping
Message mappingMessage mapping
Message mapping
 
Thompson Sampling for Machine Learning - Ruben Mak
Thompson Sampling for Machine Learning - Ruben MakThompson Sampling for Machine Learning - Ruben Mak
Thompson Sampling for Machine Learning - Ruben Mak
 
How deep learning reshapes medicine
How deep learning reshapes medicineHow deep learning reshapes medicine
How deep learning reshapes medicine
 
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical ResearchII-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
 
3 Clear And Easy Ways To Write A News Report - WikiHow
3 Clear And Easy Ways To Write A News Report - WikiHow3 Clear And Easy Ways To Write A News Report - WikiHow
3 Clear And Easy Ways To Write A News Report - WikiHow
 
Lecture1.pptx
Lecture1.pptxLecture1.pptx
Lecture1.pptx
 
Big Data Means Big Potential Challenges for Nurse Execs Response.pdf
Big Data Means Big Potential Challenges for Nurse Execs Response.pdfBig Data Means Big Potential Challenges for Nurse Execs Response.pdf
Big Data Means Big Potential Challenges for Nurse Execs Response.pdf
 
Lecture1.pptx
Lecture1.pptxLecture1.pptx
Lecture1.pptx
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Big Data, The Community and The Commons (May 12, 2014)
Big Data, The Community and The Commons (May 12, 2014)Big Data, The Community and The Commons (May 12, 2014)
Big Data, The Community and The Commons (May 12, 2014)
 

Recently uploaded

Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
MarinCaroMartnezBerg
 
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
amitlee9823
 
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
amitlee9823
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
amitlee9823
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
amitlee9823
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 

Recently uploaded (20)

Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort ServiceBDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
Call Girls Jalahalli Just Call 👗 7737669865 👗 Top Class Call Girl Service Ban...
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bellandur ☎ 7737669865 🥵 Book Your One night Stand
 
Predicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science ProjectPredicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science Project
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 
Anomaly detection and data imputation within time series
Anomaly detection and data imputation within time seriesAnomaly detection and data imputation within time series
Anomaly detection and data imputation within time series
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptx
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptx
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdfAccredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
 

3 learnings from applying Deep Learning to real world problems

  • 1.
  • 2. merantix.com Adrian Locher Establishing the future of AI in Europe Berlin AI Dr. Rasmus Rothe May 10, 2017
  • 3. 3 learnings from applying Deep Learning to real world problems Merantix GmbH, Berlin
  • 4.
  • 5. HackZurich 2017: Sep 15 - 17, 2017
  • 6.
  • 8. Neural networks in real world applications Facebook face recognition Neural networks in autonomous driving Companies working on deep learning
  • 9. How we work at Merantix Dataset Ventures Products Machine Learning
  • 10.
  • 11.
  • 12.
  • 13.
  • 15. It is actually more difficult than in theory...
  • 16.
  • 17.
  • 19. Problem: Datasets are expensive Example 1 medical diagnostics: Cost for annotating 10’000 medical images — 30min required per labelled image — 100 EUR/hour — 2 images/hour — 50 EUR/image EUR 500’000 Example 2 credit scoring: Cost of knowing if someone defaults — To estimate default risk, labels of defaulted people are required — You can only get them if you let them default EUR 10’000/d Assuming average default volume of EUR 10K
  • 20. Pretraining is the solution! Pretraining with cheap but large datasets on related domain1 Fine-tuning with well labeled data2 Performance boost!!
  • 21. How to get data for pretraining IMDB WIKI 25 36 14 51 66 34 54 18 Crawl dataPublic datasetsPretrained models ... ...
  • 22. Weakly labeled data: Medical imaging We don’t have labeled data so we get the labels from medical reports We extract text labels via NLP and use them for training How do we do this? 1 Condition 2 Prognosis Keine Pleuraerguss in der linken Lunge Keine Erguss in der linken Lunge Keine Pleuraergusses in der linken Lunge Keine Randwinkelerguss in der rechte Lunge Keine Erguß in der Lunge Word embeddings help to come up with smart rules If “Kein”/”Keine” → NO_EXISTENCE If “Einige Beweise” → SMALLER_EXISTENCE Else → DEFINITE_EXISTENCE
  • 23.
  • 24. Second learning: Caveats of real label distributions
  • 25. Academic datasets are balanced Example 1: MNIST - equally many samples per digit Example 2: Food 101 - perfectly balanced ... ... ... ... ... ... ... ... ...... TrainingsetTestset ... ... ... ... ... ... ... ... ......
  • 26. Real world datasets are not... Credit scoring Medical Imaging 1-2% of people default Luckily, the majority of people are healthy
  • 27. And: Making mistakes can be expensive Credit scoring Medical Imaging AcceptReject Paid Defaulted $ $$$$$ Diagnosed Not diagnosed Healthy Sick
  • 28. How to cope with this Sick Sick Sick Be careful Training Inference Rare class A Rare class B Frequent class Rare class A & B Frequent class 1. More data 2. Change labeling
  • 29. How to cope with this Easy: Hard: Oversampling Undersampling Negative mining Hard: Training batch Weighting of loss 3. Sampling 4. Weighting
  • 30.
  • 32. Neural networks are black boxes Lin. regression / decision trees: Decision mechanism can be easily explained Neural networks: Complex systems are hard to understand! In reality: 100m+ parameters….
  • 33. This is problematic in the real world! Why? King penguin Starfish Baseball Electric guitar +E = Panda 57.7% confidence Gibbon 99.3% confidence Can the neural network be fooled? Does it really work in production?
  • 34. This is problematic in the real world! Why? Why DIDN’T it work? What biases does it learn?
  • 35. Our Picasso Visualizer in practice Partial occlusion Saliency map Soon to be open-sourced!
  • 36. Join us on our journey Science1 Datasets2 Business3 Research on the bleeding edge of deep learning. Get access to some of the best datasets in the world. Grow businesses in the space of AI/deep learning
  • 37. WEBSITE CONTACT SOCIAL merantix.com Twitter: @merantix Github: merantix Dr. Rasmus Rothe rasmus@merantix.com