Here come the robots - Django and machine learning

Machine Learning is probably the most important development in our industry (and possibly our civilisation!). Previously restricted to math geniuses with access to supercomputers and massive data centres, machine learning tools are increasingly available as web services which are easily consumed from more traditional web applications. Python has become the lingua franca of machine learning, so Django developers are well placed to take advantage of the next wave of application development.

In this talk I outline the various machine learning platforms and provide a set of practical examples that demonstrate how Django developers can start taking advantage of artificial intelligence in their own applications. These include:

- Image recognition - using Microsoft Azure Vision to automatically caption and label the images your users upload
- Entity analysis - using the Google Cloud Natural Language API to tag news articles with people, locations and events
- Predictions - using Amazon Machine Learning to build a ‘you may also like’ feature
- Sentiment analysis - using IBM Watson to understand the tone of comments submitted to your site

Transcript

1. Here Come the Robots Django & Machine Learning Tom Dyson, DjangoCon US, October 2018
2. Machine Learning != Artifical Intelligence
4. Life 1.0 ➔ Hardware evolves ➔ Software evolves
5. Life 2.0 ➔ Designs its own software ➔ Hardware evolves
6. Life 2.1 ➔ Designs its own software ➔ Hardware evolves (with minor upgrades)
7. Life 3.0 ➔ Designs its own software ➔ Designs its own hardware
8. On the cusp ➔ Life 1.0 – 4 billion years ago ➔ Life 2.0 – 100 thousand years ago ➔ Life 3.0 – 30 years away
9. Machine learning Classical programming uses rules and data to produce answers. Machine Learning uses data and answers to produce rules. François Chollet
11. Image recognition What is this a picture of?
13. Demo
14. Practical applications ➔ ➔ Content management ➔ Accessibility ➔ NSFW ➔ Language learning
15. Sentiment analysis What is the author feeling?
17. Demo
18. Practical applications ➔ Customer support ➔ Survey tools ➔ Fake reviews ➔ News analysis ➔ Better bots
19. Entity extraction What proper nouns is this text about?
21. Demo
22. CCA video
23. Practical applications ➔ Content management ➔ Plagiarism tests ➔ Trend spotting
24. Outcome prediction What will happen next, given what we know about the past?
25. Building a model ➔ Prepare ➔ Train ➔ Evaluate ➔ Use
30. Demo
31. Practical applications ➔ Audience segmentation ➔ Donation refinement ➔ “You may also like” ➔ Happiness optimisation
34. “They literally wanted it to be an engine where I’m going to give you 100 résumés, it will spit out the top five, and we’ll hire those.” But by 2015, the company realized its new system was not rating candidates for software developer jobs and other technical posts in a gender-neutral way.
35. That is because Amazon’s computer models were trained to vet applicants by observing patterns in résumés submitted to the company over a 10-year period. Most came from men, a reflection of male dominance across the tech industry. In effect, Amazon’s system taught itself that male candidates were preferable. It penalized résumés that included the word “women’s”, as in “women’s chess club captain”.
37. Next steps ➔ If you want to learn ML ◆ Deep Learning with Python ◆ Kaggle ➔ If you want to do something with ML ◆ Read the cloud service docs ➔ Build something amazing