Introduction to Machine Learning

Transcript

1. Tiago Martinho @martinho_t tiagomartinho Introduction to Machine Learning
2. What is ML?
3. Computer science Artificial Intelligence Machine Learning Pattern Recognition and Computational Learning Theory
4. "the ability to learn without being explicitly programmed” Arthur Samuel,1959
5. "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E.” Tom M. Mitchell
6. Task Detecting Handwriting Characters
7. Task Experience Detecting Handwriting Characters Labelled Handwriting Characters
8. Task Performance Experience Detecting Handwriting Characters Detects Characters w/ Higher Accuracy Labelled Handwriting Characters
9. Why ML?
10. MNIST simple computer vision dataset ML Hello World
12. 28x28 = 784 numbers
13. uses the examples to automatically infer rules for recognising handwritten digits 0 1 2 3 4 5 6 7 8 9
14. ML Applications
15. Fraud Detection Self-Driving Cars OCR Search engines Computer Vision Health Monitoring … NLP
16. OrCam http://www.orcam.com
17. Alpha Go https://techcrunch.com/2017/05/23/googles-alphago-ai-beats-the-worlds-best-human-go-player/
18. Poker https://www.scientificamerican.com/article/time-to-fold-humans-poker-playing-ai-beats-pros-at-texas-hold-rsquo-em/
19. How it works
20. Supervised Learning
21. Supervised Learning
22. Supervised Learning General Rule Y = M*x + b
23. Supervised Learning
24. Unsupervised Learning
25. Unsupervised Learning
26. Unsupervised Learning
27. Support Vector Machine
28. SVM
29. Anomaly detection
30. Anomaly detection
31. Anomaly detection
32. Anomaly detection
33. Training Inference
34. Features
35. Collect Train Classify
36. Data 1. Train (60%) 2. Test (20%) 3. Validation (20%) Can we generalise?
40. Tiago Martinho @martinho_t tiagomartinho Thank you!