PART 1: OVERVIEW & INTRO
MACHINE LEARNING
WHY MACHINE LEARNING
BACKGROUND, PYTHON AND ML
▸ It’s about building things. Ability to “know” user.

Back-end web development and Data Science
▸ Mathematics and APIs
▸ Scikit-learn, environment and dependencies
APPLICATIONS OF MACHINE LEARNING
RECENT EXAMPLES
▸ Yelp: 

http://engineeringblog.yelp.com/2015/10/how-we-use-deep-learning-
to-classify-business-photos-at-yelp.html
▸ Airbnb:

http://nerds.airbnb.com/aerosolve/
▸ Spotify: 

http://benanne.github.io/2014/08/05/spotify-cnns.html
▸ Netflix: 

http://techblog.netflix.com/2015/07/tracking-down-villains-outlier.html
▸ Spam, Medical, Finance
WHAT IS MACHINE LEARNING?
5 TRIBES OF MACHINE LEARNING
Tribe Origins Master Algorithm
Symbolists Logic, philosophy Inverse Deduction
Connectionists Neuroscience Back propagation
Evolutionaries Evolutionary Biology Genetic Programming
Bayesian Statistics Probabilistic Inference
Analogizes Psychology Kernel Machines
Source: Ex-1
GETTING STARTED
ENVIRONMENT AND SCIKIT-LEARN
▸ Build and run the Docker Notebook for dependencies:

https://github.com/ipython/docker-notebook/tree/master/
scipyserver
▸ Clone Scipy 2013 Scikit-learn Tutorial into /notebooks

https://github.com/jakevdp/sklearn_scipy2013
▸ Working with Scipy Stack: 

Ipython notebook, Matplotlib, Numpy
▸ Scikitlearn API: Basic Classification and Regression
WHAT IS MACHINE LEARNING?
CHOOSING AN ALGORITHM
Source: Ex-2
MOVING FORWARD
BUILD AND LEARN
▸ Kaggle: https://www.kaggle.com/
▸ Yelp Dataset Challenge 

http://www.yelp.com/dataset_challenge
▸ Machine Learning Coursera with Prof Domingos

https://www.coursera.org/course/machlearning
RESOURCES
RESOURCES
▸ 1: Professor Domingos Five Tribes of Machine Learning

http://www.slideshare.net/SessionsEvents/pedro-domingos-professor-
university-of-washington-at-mlconf-atl-91815
▸ 2: Scikit-learn Algorithm Cheat Sheet

http://scikit-learn.org/stable/themes/scikit-learn/static/
ML_MAPS_README.html
▸ 3: Docker Notebook: 

https://github.com/ipython/docker-notebook/tree/master/scipyserver
▸ 4: Scipy 2013 Scikit-learn Tutorial

https://github.com/jakevdp/sklearn_scipy2013

Machine Learning Environment and Intro

  • 1.
    PART 1: OVERVIEW& INTRO MACHINE LEARNING
  • 2.
    WHY MACHINE LEARNING BACKGROUND,PYTHON AND ML ▸ It’s about building things. Ability to “know” user.
 Back-end web development and Data Science ▸ Mathematics and APIs ▸ Scikit-learn, environment and dependencies
  • 3.
    APPLICATIONS OF MACHINELEARNING RECENT EXAMPLES ▸ Yelp: 
 http://engineeringblog.yelp.com/2015/10/how-we-use-deep-learning- to-classify-business-photos-at-yelp.html ▸ Airbnb:
 http://nerds.airbnb.com/aerosolve/ ▸ Spotify: 
 http://benanne.github.io/2014/08/05/spotify-cnns.html ▸ Netflix: 
 http://techblog.netflix.com/2015/07/tracking-down-villains-outlier.html ▸ Spam, Medical, Finance
  • 4.
    WHAT IS MACHINELEARNING? 5 TRIBES OF MACHINE LEARNING Tribe Origins Master Algorithm Symbolists Logic, philosophy Inverse Deduction Connectionists Neuroscience Back propagation Evolutionaries Evolutionary Biology Genetic Programming Bayesian Statistics Probabilistic Inference Analogizes Psychology Kernel Machines Source: Ex-1
  • 5.
    GETTING STARTED ENVIRONMENT ANDSCIKIT-LEARN ▸ Build and run the Docker Notebook for dependencies:
 https://github.com/ipython/docker-notebook/tree/master/ scipyserver ▸ Clone Scipy 2013 Scikit-learn Tutorial into /notebooks
 https://github.com/jakevdp/sklearn_scipy2013 ▸ Working with Scipy Stack: 
 Ipython notebook, Matplotlib, Numpy ▸ Scikitlearn API: Basic Classification and Regression
  • 6.
    WHAT IS MACHINELEARNING? CHOOSING AN ALGORITHM Source: Ex-2
  • 7.
    MOVING FORWARD BUILD ANDLEARN ▸ Kaggle: https://www.kaggle.com/ ▸ Yelp Dataset Challenge 
 http://www.yelp.com/dataset_challenge ▸ Machine Learning Coursera with Prof Domingos
 https://www.coursera.org/course/machlearning
  • 8.
    RESOURCES RESOURCES ▸ 1: ProfessorDomingos Five Tribes of Machine Learning
 http://www.slideshare.net/SessionsEvents/pedro-domingos-professor- university-of-washington-at-mlconf-atl-91815 ▸ 2: Scikit-learn Algorithm Cheat Sheet
 http://scikit-learn.org/stable/themes/scikit-learn/static/ ML_MAPS_README.html ▸ 3: Docker Notebook: 
 https://github.com/ipython/docker-notebook/tree/master/scipyserver ▸ 4: Scipy 2013 Scikit-learn Tutorial
 https://github.com/jakevdp/sklearn_scipy2013