Adding machine learning to a web app

Pretty much the simplest thing you can do to get started with machine learning in a web app. These are my slides from BathCamp AI night.

Transcript

1. Adding machine learning to a web app Richard Dallaway @d6y
2. It’s easy, right? 1. Get some data 2. Find magic stats & algorithms 3. Predict the future!
3. It’s easy, right? 1. Get some data 2. Find magic stats & algorithms 3. Predict the future! that helps solve the problem frame the problem explore the data pilot what’s success? does this help users? UI impact? behaviour changes?
4. Make it easier for users to #tag todos
6. tag
7. Can we suggest tags as a task is typed in?
8. Can we suggest tags as a task is typed in? useful
9. Where to start? from “Algorithms of the Intelligent Web”
10. “Google uses Bayesian filtering the way Microsoft uses the if statement" as told to Joel Spolsky
11. A contrived example #home 40% #work 60% “windows” 50% “fix” 50% “windows” 16.6% “fix” 83.4% p(#home | “fix”, “windows”) ?
12. A contrived example #home 40% #work 60% “windows” 50% “fix” 50% “windows” 16.6% “fix” 83.4% p(#home | “fix”) = 40% x 50% (40% x 50%) + (83.4% x 60%) = about 28%
13. A contrived example #home 28% #work 72% “windows” 50% “fix” 50% “windows” 16.6% “fix” 83.4% p(#home | “fix”, “windows”) = 28% x 50% (28% x 50%) + (16.6% x 72%) = about 55% p(#home | “fix”)
14. p(C | e) = P(C) x P(e | C) P(e)
15. p(C | e) = P(C) x P(e | C) P(e) “the estimation of P(e | C) can be viewed as the central issue in designing learning systems. ” — Weiss & Kulikowski “Computer Systems that Learn”
16. Demo: addsharedo.com with tag suggestions
17. results of running the model
18. It’s easy, right? 1. Explore the data 2. Frame your problem 3. Measure the performance honestly
19. Write it yourself? Find a library? Ask Google to do it for you? How to build? ...but pilot with offline data first.
20. www.manning.com 40% off with bathcamp40 until August 10th
21. Questions? or later: @d6y richard@SpiralArm.com