Machine Learning: Introduction Jens Kauffmann Max–Planck–Institut für Radioastronomie
Example I: Classification of hand–written Digits Jens Kauffmann ● MPIfR 2
Example I: Classification of hand–written Digits training of classifier Jens Kauffmann ● MPIfR 3
Example I: Classification of hand–written Digits free parameter => verification needed! Jens Kauffmann ● MPIfR 4
Example II: Classification just uses complex Boundaries Jens Kauffmann ● MPIfR 5
Example II: Classification just uses complex Boundaries Jens Kauffmann ● MPIfR 6
Machine Learning: Needs Verification! different methods => different results no verification, no parameter adjustment => nonsensical results Jens Kauffmann ● MPIfR 7
Survey of Methods I Jens Kauffmann ● MPIfR 8
Survey of Methods II Jens Kauffmann ● MPIfR 9
Survey of Methods III (a) well–separated categories (b) overlapping categories Jens Kauffmann ● MPIfR 10
References & Literature ● Scikit learn Python packages: ● emcee ● pymc ● Seaborn (for graphics) ● Scikit Tutorial „An Introduction to Machine Learning“ short texts to get started: ● Scikit Tutorial „A Tutorial on Statistical Learning“ rather for people writing ML algorithms? ● „The Elements of Statistical Learning" free books: ● „An Introduction to Statistical Learning" ● „An Introduction to Machine Learning“ (Springer Link; free at MPIfR) ● „Python Data Science Handbook“, section „Machine Learning“ Jens Kauffmann ● MPIfR 11
Exercises schedule: Thursday, Feb. 16, 13:00 Tuesday, Feb. 21, 13:00 Wednesday, Feb. 22, 13:30 preparations: get Python 3.6 via Anaconda (https://www.continuum.io/downloads) learn how to start a Jupyter notebook familiarize yourself with Scikit learn (http://scikit-learn.org) Jens Kauffmann ● MPIfR 12
Recommend
More recommend