Rage Against The Learning of the Machine

Transcript

1. RAGE AGAINST 
 THE LEARNING OF THE MACHINE ERRAZUDIN ISHAK

   PYCON APAC 2017

2. AGENDA ABOUT ME WHAT ON EARTH FOR WHAT REASON SO

   HOW TO DO THAT SUMMARY PYCON APAC 2017

3. ABOUT ME Data Masseuse Solutions Architect DevOps Freak Bitcoin Farmer

   :) PYCON APAC 2017

4. I WAS HERE 2009: foss.my, MyGOSSCON 2010: PHP North West

   (UK), Entp. PHP Techtalk, BarcampKL, MOSC.my, MyGOSSCON 2011: Wordpress Conf. Asia, Joomla! Day KL, MOSC.my, OWASP Day KL PYCON APAC 2017

5. I WAS HERE 2012: OWASP AppSec APAC (Sydney), MOSC.my 2013:

   OSDC (Auckland), MOSC.my 2016: SCM Workshop UMP PYCON APAC 2017

6. WHAT ON EARTH? PYCON APAC 2017

7. WHAT ON EARTH? PYCON APAC 2017 ML

8. –Tom M.Mitchell, CMU “A computer program is said to learn

   from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E.” TYPICAL EXPLANATION…..

9. WHAT ON EARTH? PYCON APAC 2017 Source : NVIDIA

10. FOR WHAT REASON PYCON APAC 2017 “…it is now the

    golden age of Machine Learning” –Random guy “… because big guys (Google and Facebook) work on it” –Another random guy

11. FOR WHAT REASON PYCON APAC 2017

12. FOR WHAT REASON Web Search & Recommendation Engines Finance :

    Stock, Fraud, Credit Check Healthcare : Drug Discovery, Computational Biology Text, Speech, Object Recognition Space, Astronomy PYCON APAC 2017

13. FOR WHAT REASON PYCON APAC 2017 “Drawing lines through data”

14. FOR WHAT REASON PYCON APAC 2017

15. FOR WHAT REASON PYCON APAC 2017 Classification : “Draw lines

    to separate data” Source : ML Berkeley Labelled Data Decision Boundary (D.B.) More complicated algo,
 More complicated D.B. FOR WHAT REASON

16. FOR WHAT REASON PYCON APAC 2017 Regression : “Draw lines

    to describe data” Source : ML Berkeley Labelled Data Probability Predictor FOR WHAT REASON

17. FOR WHAT REASON PYCON APAC 2017 Source : Brown EDU

18. SO HOW TO DO THAT Formulate the problem Design the

    solution Bring up the data Technology to master Build ML model Evaluate, fine tune the quality Package it nicely PYCON APAC 2017

19. FORMULATE YOUR PROBLEM What : Describe it Why : Benefits

    How : The flow (step-by-step) PYCON APAC 2017

20. BRING UP THE DATA Prepare (the right) Data Identify Outliers

    Data Pre-Processing PYCON APAC 2017

21. TECHNOLOGIES “Right tools for the right job” PYCON APAC 2017

22. BUILD THE MODEL PYCON APAC 2017 The most challenging part

    Build, Train, Test, Repeat

23. FINE TUNING Test harness Measuring the performance Datasets (Test, Training)

    PYCON APAC 2017

24. FINE TUNING “If You Knew Which Algorithm or Algorithm Configuration

    To Use,
 You Would Not Need To Use Machine Learning”
 
 - Jason Brownlee, PhD PYCON APAC 2017

25. PRESENTATION PYCON APAC 2017

26. SAMPLE #1 PYCON APAC 2017

27. FORMULATE YOUR PROBLEM PYCON APAC 2017 Toyota’s stock price on

    January 6th 2017

28. FORMULATE YOUR PROBLEM PYCON APAC 2017 Ford’s stock price on

    January 4th 2017

29. DESIGN THE SOLUTION PYCON APAC 2017 trump2cash
 Python
 Google Cloud

    Natural Language API
 Wikidata Query Service
 Tradeking API

30. BUILD (PLAY WITH) THE MODEL PYCON APAC 2017

31. PRESENTATION PYCON APAC 2017

32. PRESENTATION PYCON APAC 2017

33. SAMPLE #2 : SPAM DETECTION PYCON APAC 2017 ML problem:

    text classification Algorithms: naive bayes, linear classifiers, tree classifiers, all-you-want classifiers Technologies: sklearn, nltk, scrapy Data: sms spam dataset, e-mail spam dataset , youtube comments spam dataset

34. SUMMARY PYCON APAC 2017 Source : Google Cloud Next 2017

35. THANK YOU We’re Hiring errazudin.ishak@gmail.com PYCON APAC 2017