ML Session n°1

Transcript

1. ML: concepts January 2017
2. Format Slack channel : #ml-courses • Today : concepts • 08 Feb : understanding a ML project : what are the good questions? • 20 Feb and following : ◦ more technical sessions ◦ optional “homework” between sessions (small projects) ◦ current plan : 7 technical sessions ◦ goal : be able to work on ML projects autonomously
3. Machine Learning
4. Hierarchy
5. Explaining Machine Learning Machine learning is the idea that there are generic algorithms that can tell you something interesting about a set of data without you having to write any custom code specific to the problem. Instead of writing code, you feed data to the generic algorithm and it builds its own logic based on the data.
6. Machine Learning vs Statistics ? They are both concerned with the same question: how do we learn from data? Statistics Machine Learning Estimation Learning Classifier Hypothesis Data Point Example/ Instance Regression Supervised Learning Classification Supervised Learning Covariate Feature Response Label
7. Inputs Raw data Multimedia (sound, pictures, videos) Language
8. ML vs “traditional” methods
9. Minksy’s Multiplicity (1960) Crucial parts for problem solving : • Induction • Planning • Search, knowledge representation • Pattern recognition • Learning Components needed to get to human-level AI
10. Minksy’s Multiplicity (1960) Crucial parts for problem solving : • Induction • Planning • Search, knowledge representation • Pattern recognition • Learning Components needed to get to human-level AI
11. Topics for Machine Learning • Self-driving cars • Human interaction : ◦ Handwriting ◦ Speech ◦ Natural language • OCR • Image recognition • Information retrieval • Artificial personal assistants • Recommendations systems • Drones • Game playing • ...
12. Subdomains
13. Subdomains of Machine Learning Machine Learning Supervised Learning Unsupervised Learning Reinforcement Learning
14. Supervised learning
15. Supervised learning Labelled data Classification Regression
16. Demo: Intro to Machine Learning http://www.r2d3.us/ visual-intro-to- machine-learning-part-1/
17. Unsupervised learning
18. Unsupervised learning
19. Reinforcement learning
20. Reinforcement learning
21. Reinforcement Learning: OpenAI
22. First intuitions
23. Linear regression
24. Intuitions from linear regression • algorithm is generic, results depends on data • system is both the algorithm and the data • only as good as your data • starts with a hypothesis about how we can represent the data (for linear regression : a straight line) • can deal poorly with outliers • lots of calculation to learn, but very fast to apply (can run on mobile)
26. Tools
27. Artificial Neural Networks (ANN) Each node does a linear combination of previous nodes More nodes can handle more complexity Training in multiple steps - left to right to evaluate the training set - right to left to propagate errors
28. Demo: Tensorflow Playground
29. Deep learning
30. Deep learning
31. Convolutional neural networks
32. Demo: MNIST
33. Recurrent neural networks
34. Generative Adversial Nets
35. State of the art
37. IBM Watson • Healthcare : ◦ Diagnostics ◦ Tests suggestion ◦ Prescription recommendations • Legal : ◦ Hired as a lawyer (“Ross”) • Teaching : ◦ Used as a TA (“Jill Watson”) • Cooking : ◦ published a recipe book ◦ new combinations ◦ able to avoid allergies
38. Google Auto captionning (2014) Two pizzas sitting on top of a stove top oven
40. Cloud Vision API Available on Google Cloud Automatic labelling Sentiment analysis Text extraction Landmark detection Logo detection Explicit content detection
41. SyntaxNet and Parsey McParseface
42. SyntaxNet and Parsey McParseface
43. SyntaxNet and Parsey McParseface Parsey McParseface can correctly read: • The old man the boat. • While the man hunted the deer ran into the woods. • While Anna dressed the baby played in the crib. • Buffalo buffalo Buffalo buffalo buffalo buffalo Buffalo buffalo. It makes mistakes on: • I convinced her children are noisy. • The coach smiled at the player tossed the frisbee. • The cotton clothes are made up of grows in Mississippi. • James while John had had had had had had had had had had had a better effect on the teacher
44. Demo: Pride and Prejudice
45. Google Translate
46. Google Translate
47. Google Translate
48. NeuralArt (Tensorflow) Content Style Output
49. Facial manipulation (Feb 2015)
50. Face recognition (April 2014)
51. Finding similarities in art (Aug 2014)
52. Audio prediction on video (April 2016)
53. Predicting scene from sound
54. Extract instructions from Youtube videos (Nov 2015)
55. Reading old journals
56. Creating videos of the future
57. Applications of NLP at Quora - automatic grammar correction - question quality - duplicate question detection - related question suggestion - topic biography quality (= qualifications of writer) - topic labeler (from “science” to narrow topics like “tennis Courts in Mountain View”) - search - answer summaries - automatic answers wiki - hate speech/harassment detection - spam detection - question edit quality
58. Questions? January 2017