Teaching Machine Learning

Teaching Machine Learning

Insights on how to teach machine learning and deep learning.
The entry barrier is not that high!
Video: https://www.youtube.com/watch?v=dyoxtDhUR74
Conference: https://pydata.org/warsaw2017/

1b324e4900e79878eb518c1263b41795?s=128

Piotr Migdał

October 19, 2017
Tweet

Transcript

  1. 2.

    PhD in quantum physics theory (2014, ICFO, Barcelona) data scientist

    (deepsense.ai / consultant)
 machine learning deep learning data-viz (D3.js)
  2. 4.
  3. 6.
  4. 7.

    A person first learns classical mechanics • …by playing with

    balls, blocks? • …by learning Newton laws, differential calculus?
  5. 8.

    A person first learns natural numbers • …by counting apples,

    toys? • …by the von Neumann construction?
  6. 9.

    i ~ ˙ = ⇣ ~2 2m r2 + V

    ( x ) ⌘ ˆ H = E
  7. 13.

    A person first learns machine learning • ...by studying computer

    science, mathematics
 and statistics for years?
  8. 14.

    you don’t understand Machine Learning unless you can teach it

    with pen&paper (or at least - JavaScript)
  9. 15.
  10. 23.
  11. 24.
  12. 25.
  13. 28.

    Things which are not problems • I don’t know Python

    • They are only high-school • They are not from STEM
  14. 31.

    Problems with teachers • Too much math details & too

    little insight • Too much historical inertia • No plots • Too little real data
 (e.g. all np.random.randn(n, m))
  15. 33.

    Pragmatic algorithms • kNN • Linear + Logistic
 Regression •

    Random Forest • XGBoost • Neural Networks
  16. 34.

    Problems with clients • Everyone is an “expert” • Squeezing

    one semester (or a few)
 into a few days (or just one) • Deep learning will solve all our problems • Installation!!!