Statistical Machine Learning
Lectures are Monday and Wednesday 10:15-11:30 online via BigBlueButton (URL has been sent out, or ask me via email).
Recitations are Wednesdays, 11:45-12:30 online via Zoom (meeting details have been sent out, or ask TAs via email).
Instructors: Christoph Lampert
Teaching Assistant: Alex Peste,   Bernd Prach

announcements schedule references



Date   Lecture Topic Slides Assignments
Oct 05 Mon 1 A Hands-On Introduction PDF exercise sheet 1: PDF
data: wine-train.txt, wine-test.txt
Oct 07 Wed 2 Bayesian Decision Theory,
Generative Probabilitistic Models
Oct 12 Mon 3 Discriminative Probabilistic Models PDF exercise sheet 2: PDF  
Oct 14 Wed 4 Maximum Margin Classifiers PDF
Oct 19 Mon 5 Model Evaluation; Regularization; Model Selection PDF exercise sheet 3 PDF  
data: XtrainIMG.txt, Ytrain.txt
Oct 21 Wed 6 Bias/Fairness; Transfer Learning PDF
Oct 26 Mon - no lecture (national holiday) exercise sheet 4 PDF (v1.1 fixed error on Nov 1st)
data: XtestIMG.txt, Ytest.txt XtrainIMG2.txt, Ytrain2.txt
Oct 28 Wed 7 Learning Theory I PDF  
Nov 2 Mon 8 Learning Theory II PDF
extra notes: PDF
exercise sheet 5 PDF final project PDF
Nov 4 Wed 9 Learning Theory III, Deep Learning I PDF  
Nov 9 Mon 10 Deep Learning II PDF no exercise sheet
Nov 11 Wed 11 Deep Learning III PDF  
Nov 16 Mon 12 Project Presentations  
Nov 18 Wed 13 Buffer  


[1] Christopher Bishop: Pattern Recognition and Machine Learning, Springer, 2007.
[2] Mohri, Rostamizadeh, Talwalkar: Foundations of Machine Learning, MIT Press, 2012.
[3] Shalev-Shwartz, Ben-David: Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press, 2014.
[4] Hal Daume III: A Course in Machine Learning, online.
[5] Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong: Mathematics for Machine Learning, online.
[6] Solon Barocas, Moritz Hardt, Arvind Narayanan: Fairness and Machine Learning, online
[7] Ian Goodfellow, Yoshua Bengio, Aaron Courville: Deep Learning, online
... and many others

announcements schedule references