PyTexas - Machine learning APIs by Example

Imagine you could easily use ML without having a PhD or having to mess with models or interacting with TensorFlow? Imagine ML working for your application, not you working for ML. In this session learn how to use ML APIs through demos to power your application and focus on what matters!

Transcript

1. Machine Learning APIs by Example Gabriela D'Ávila Ferrara Developer Advocate @gabidavila | gabi.dev
2. What is Machine Learning? @gabidavila
3. Solving problems without specific rules. Learning by example and experience. @gabidavila
4. "Machine learning is a thing-labeler, essentially" @gabidavila
5. Exercise @gabidavila
6. How would you identify the following images? @gabidavila
7. @gabidavila
8. @gabidavila
10. Dog or muffin? source: boredpanda.com
11. And this? source: boredpanda.com
12. @gabidavila ML is/helps with... Solving problems without explicitly knowing the solution Loosely based on how the human brain learns Enable systems that improve over time
13. Available ML APIs Cloud Natural Language Cloud Vision Cloud Translation Cloud Speech Cloud Video Intelligence #WOCinTech @gabidavila
14. 14 @SRobTweets Cloud Vision
15. Complex image detection with a simple REST request. @gabidavila
16. Label & web detection OCR Logo detection Explicit content detection Crop hints Landmark detection
17. Demo @gabidavila
18. Cloud Vision API call using Python @gabidavila
19. Cloud Vision in production: GIPHY Access for more information: Engineering.giphy.com @GIPHYEng @gabidavila
20. Cloud Translation
21. Translate text into 100+ languages. @gabidavila
22. Translate text Detect language
23. Cloud Vision & Cloud Translation
24. Demo @gabidavila
25. Cloud Translate API call using Python @gabidavila
26. Cloud Natural Language
27. Understand text with a simple REST API request. @gabidavila
28. Extract entities Detect sentiment Analyze syntax Classify content
29. Entities I went to the ⟨restaurant⟩ 2 and ordered ⟨sushi⟩ 1 . The ⟨food⟩ 3 was really good. Localization 2. restaurant Consumer Good 1. sushi Other 3. food @gabidavila
30. Sentiment score magnitude Document 0.3 0.9 I went to the restaurant and ordered sushi. -0.1 0.1 The food was really good. 0.8 0.8 Score Range -1.0 — -0.25 -0.25 — 0.25 0.25 — 1.0 Negative Neutral Positive @gabidavila
31. Syntax Analysis @gabidavila
32. @gabidavila
33. Content Classification Rafael Montero Shines in Mets’ Victory Over the Reds. Montero, who was demoted at midseason, took a one-hitter into the ninth inning as the Mets continued to dominate Cincinnati with a win at Great American Ball Park. { categories: [ { name: '/Sports/Team Sports/Baseball', confidence: 0.99 } ] } @gabidavila
34. Demo @gabidavila
35. Get to know more about the APIs Vision: cloud.google.com/vision Video: cloud.google.com/video-intelligence Speech: cloud.google.com/speech Translation: cloud.google.com/translation Natural Language: cloud.google.com/natural-language Thank you! @gabidavila gabi.dev @gabidavila