Machine Learning for Everyone
11 likes•2,117 views
The document outlines a machine learning agenda aimed at encouraging widespread use of the technology, addressing common misconceptions such as perceived complexity and high costs. It presents various applications of machine learning, including diagnosing tuberculosis, classifying products, and crime clustering, utilizing different algorithms like neural networks and random forests. The document emphasizes accessibility through online courses and tools, suggesting that machine learning is achievable for everyone.
Machine Learning for Everyone
- 2. Agenda Goal: Encourage you to use Machine Learning… today! ‣ Aboutme ‣ MachineLearning Misconceptions Concepts Problems andAlgorithms ‣ ForEveryone!
- 3. About me Electronics Engineering, Software Development, Data Science… Why not?
- 4. Neural TB Tool that aids in the diagnosis ofTuberculosis using Neural Networks
- 5. Neural Ringer Algorithm for online electron/jet discrimination forthe ATLAS detector at CERN using Neural Networks
- 6. djBrazil Intelligent music platform specialized in Brazilian music
- 7. Jigsaw Dots Interactive exploratory visualization of employees based on their skills
- 9. Machine Learning It is all about learning
- 10. Misconceptions Too difficult Big upfront investments Needs supercomputers Only for PhDs from MIT Data Silo Takes too long to pay off ƃ
- 11. Reality ♥
- 12. Feature Extraction Item { Feature 1 Feature 2 Feature 3 … Feature N Feature2 0 8 16 24 32 40 Feature 1 0 10 20 30 40 50 60 70 80 90
- 13. Supervised Learning 23, 45, 67, 78 12, 48, 68, 22 … 34, 58, 77, 19 3 2 … 5 20, 39, 59, 68 3 ♥ Items Features Labels Algorithm New Item PredictionFeatures Model
- 14. Supervised Learning Algorithms K-Nearest Neighbors Neural Networks DecisionTree Random Forest
- 15. Regression 921 37 23 2487 1541 21 2121 21 ?
- 16. Boston housing prices Prediction of house prices at Boston suburbs based on census data using Linear Regression
- 17. Classification BA B A AB AB A AB B ?
- 18. Detecting particles Online electron detection based on more than 1500 detector cells using Neural Networks (GeV)TE 0 10 20 30 40 50 60 70 80 o(%)a ~ Prob.deRejeic 20 30 40 50 60 70 80 90 100 Ringer T2Calo smicosoC η -2 -1 0 1 2 o(%)a ~ Prob.deRejeic 80 85 90 95 100 Ringer T2Calo φ -3 -2 -1 0 1 2 3 o(%)a ~ Prob.deRejeic 90 92 94 96 98 100 Ringer T2Calo
- 19. Classifying products Product classification on 9 different classes based on 90 numerical features usingAmazon Machine Learning
- 20. Diagnosing Tuberculosis Tuberculosis diagnosis based on patients questionnaires using Neural Networks
- 21. Unsupervised Learning 23, 45, 67, 78 12, 48, 68, 22 … 34, 58, 77, 19 20, 39, 59, 68 ♥ Items Features Algorithm New Item Better RepresentationFeatures Model
- 22. Unsupervised Learning Algorithms K-Means Self-Organising Maps t-SNE
- 23. Clustering
- 24. Clustering crime Crime clusters based on information from the San Francisco Police Department Crime Incident Reporting system using K-means
- 26. Visualizing employees Visualization of 2000+ employees described by 200+ skills after reducing dimensionality using the t-SNE algorithm
- 27. For everyone! You can do it!
- 28. Massive Online Open Courses
- 30. Pay-as-you-go Amazon Machine Learning Google Cloud Machine Learning Azure Machine Learning
- 31. Cheat sheets
- 33. Code Snippet >>> classifier = RandomForestClassifier().fit(features, labels) >>> prediction = classifier.predict(new_features) 23, 45, 67, 78 12, 48, 68, 22 … 34, 58, 77, 19 A B … B 20, 39, 59, 68 A ♥ Items Features Labels Algorithm New Item PredictionFeatures Model