This document discusses predictive apps for startups using machine learning. It provides examples of everyday use cases like real estate price prediction and email spam detection. It explains that machine learning works by training a model on data and then using the model to make predictions on new data. The document also discusses how to make machine learning more accessible through cloud platforms and APIs, and how automation tools can help simplify machine learning tasks like model tuning and algorithm selection.

1. Predictive Apps for Startups
@louisdorard
#MLVLC - 11 March 2016

2. AI is everywhere

10. Lars Trieloff
@trieloff
(see source)

11. @louisdorard

12. How does it work?

13. Data + Machine Learning

15. Bedrooms Bathrooms Surface (foot²) Year built Type Price ($)
3 1 860 1950 house 565,000
3 1 1012 1951 house
2 1.5 968 1976 townhouse 447,000
4 1315 1950 house 648,000
3 2 1599 1964 house
3 2 987 1951 townhouse 790,000
1 1 530 2007 condo 122,000
4 2 1574 1964 house 835,000
4 2001 house 855,000
3 2.5 1472 2005 house
4 3.5 1714 2005 townhouse
2 2 1113 1999 condo
1 769 1999 condo 315,000

16. Bedrooms Bathrooms Surface (foot²) Year built Type Price ($)
3 1 860 1950 house 565,000
3 1 1012 1951 house
2 1.5 968 1976 townhouse 447,000
4 1315 1950 house 648,000
3 2 1599 1964 house
3 2 987 1951 townhouse 790,000
1 1 530 2007 condo 122,000
4 2 1574 1964 house 835,000
4 2001 house 855,000
3 2.5 1472 2005 house
4 3.5 1714 2005 townhouse
2 2 1113 1999 condo
1 769 1999 condo 315,000

18. Bedrooms Bathrooms Surface (foot²) Year built Type Price ($)
3 1 860 1950 house 565,000
3 1 1012 1951 house
2 1.5 968 1976 townhouse 447,000
4 1315 1950 house 648,000
3 2 1599 1964 house
3 2 987 1951 townhouse 790,000
1 1 530 2007 condo 122,000
4 2 1574 1964 house 835,000
4 2001 house 855,000
3 2.5 1472 2005 house
4 3.5 1714 2005 townhouse
2 2 1113 1999 condo
1 769 1999 condo 315,000

19. ML is a set of AI techniques where
“intelligence” is built from
examples

21. “Weak AI” vs. “Strong AI”

22. 22
Everyday use cases
• Real-estate
• Spam
• Priority inbox
• Crowd prediction
property price
email spam indicator
email importance indicator
location & context #people
Zillow
Gmail
Gmail
Tranquilien

23. Making Machine Learning accessible
with cloud platforms

25. HTML / CSS / JavaScript

26. HTML / CSS / JavaScript

27. squarespace.com

30. The two phases of ML
• TRAIN a model
• PREDICT with a model
30
Machine Learning APIs

31. The two methods of ML Application Programming Interfaces
(here in Python)
• model = create_model(‘training.csv’)
• predicted_output, confidence =
create_prediction(model, new_input)
31
Machine Learning APIs

32. The two methods of ML Application Programming Interfaces
(here in Python)
• model = create_model(‘training.csv’)
• predicted_output, confidence =
create_prediction(model, new_input)
32
Machine Learning APIs

33. Example request to BigML API
$ curl https://bigml.io/dev/model?$BIGML_AUTH
-X POST
-H "content-type: application/json"
-d '{"dataset": "dataset/50ca447b3b56356ae0000029"}'

35. • Classification problem
• Features:
• Text of email
• Sender in address book?
• How often do I reply?
• How quickly do I reply?
• Demo
35
Priority detection

37. • VM with Jupyter notebooks (Python & Bash)
• API wrappers preinstalled: BigML & Google Pred
• Notebook for easy setup of credentials
• Scikit-learn and Pandas preinstalled
• Open source VM provisioning script & notebooks
• Search public Snaps on terminal.com:“machine learning”
37
Getting started

38. Making Machine Learning easier

39. How was it before?
from sklearn import svm
model = svm.SVC(gamma=0.001, C=100.)
from sklearn import datasets
digits = datasets.load_digits()
model.fit(digits.data[:-1], digits.target[:-1])
model.predict(digits.data[-1])

40. How was it before?
from sklearn import svm
model = svm.SVC(gamma=0.001, C=100.)
from sklearn import datasets
digits = datasets.load_digits()
model.fit(digits.data[:-1], digits.target[:-1])
model.predict(digits.data[-1])
WAT?

41. http://oscar.sensout.com

42. • Spearmint:“Bayesian optimization”for tuning parameters →
Whetlab → Twitter
• Auto-sklearn:“automated machine learning toolkit and drop-
in replacement for a scikit-learn estimator”
42
Open Source AutoML libraries

43. Scikit
from sklearn import svm
model = svm.SVC(gamma=0.001, C=100.)
from sklearn import datasets
digits = datasets.load_digits()
model.fit(digits.data[:-1], digits.target[:-1])
model.predict(digits.data[-1])

44. Scikit
from sklearn import svm
model = svm.SVC(gamma=0.001, C=100.)
from sklearn import datasets
digits = datasets.load_digits()
model.fit(digits.data[:-1], digits.target[:-1])
model.predict(digits.data[-1])

45. AutoML Scikit
import autosklearn
model = autosklearn.AutoSklearnClassifier()
from sklearn import datasets
digits = datasets.load_digits()
model.fit(digits.data[:-1], digits.target[:-1])
model.predict(digits.data[-1])

46. • Algorithm selection… AutoML
• Scaling… Azure ML or Yhat (Greg at PAPIs Connect)
• “Automating ML workflows: a report from the trenches”—
Jose A. Ortega Ruiz
46
Automatization

47. Making Deep Learning accessible

48. • Classification problem
• Input is an image = pixel values
• Deep Learning! (with Vincent)
48
Image categorization

49. 49
Machine Learning for person detection
pixel1 pixel2 pixel3 person?
102 0 255 Yes
35 41 209 No
… … … …

50. • Neural network:
• Layers
• Neurons of one layer connected to
neurons of next layer
• Each neuron receives signals from
previous layer and sends new signal to
next layer
• New signal based on linear combination
of signals received
• “Deep”-> more than 3 layers
50
Deep Learning

51. 51
Deep Learning for animal detection

52. 52
Deep Learning for animal detection
pixel1
pixel2
pixel3
cat
dog
1st layer
value=(102, 0, 255)
Last layer
value=(0.1, 0.7, 0.4)
Output
value=(0.8, 0.3) => there’s
probably a cat!

53. 53
Deep Learning for animal detection
pixel1
pixel2
pixel3
cat
dog
1st layer
value=(4, 166, 23)
Last layer
value=(0.1, 0.7, 0.4)
Output
value=(0.1, 0.2) => probably no
animal here

54. pixel1
pixel2
pixel3
cat
dog
1st layer
value=(102, 0, 255)
Output
value=(0.8, 0.3) => there’s
probably a cat!
Last layer
value=(0.1, 0.7, 0.4)

55. 55
Machine Learning for person detection
pixel1 pixel2 pixel3 person?
102 0 255 Yes
35 41 209 No
… … … …
• Use network for animal detection until last layer
• Replace images with“smart”representation given by last layer
neuron1 neuron2 neuron3 person?
0.1 0.2 0.5 Yes
0.8 0.3 0.8 No
… … … …

57. • Artificial Intelligence for Business and Society
• Next Monday & Tuesday
• papis.io/connect
• Discount for 24 hours only!
57
PAPIs Connect