Instructors: Bernd Bickel, Christoph Lampert, Gasper Tkacik
Teaching Assistants: Bor Kavcic, Katharina Ölsböck
The course will consist of 3 segments of approximately 4 weeks each. Each segment will follow the same structure: the first two weeks will consist mainly of lectures and background material study, the second two weeks will introduce a small project based on real data or a computational assignment, whose results will then be presented in the last week. The emphasis will be on dealing with data and computations in a hands-on fashion.
Tentative summary of the course segments:
Goal: understand and be able to handle predictive models
Goal: Characterizing basic statistical properties of an unknown dataset
Segment 3: Simulations and numerics (Instructor: Bernd Bickel)
Goal: Understand and apply basic computational techniques for simulations in a variety of applied science problems, with focus on differential equations
Segment 2 Lecture Notes, Homework and Project (updated May 15, 2017)
Segment 2 trace1 Data (zipped text file).
Segment 2 trace2 Data (zipped text file).
Segment 2 Ruderman images Data (zipped text files).
|Feb 27||predictive models, least squares regression, model selection, regularization||slides (PDF)|
|Mar 1||real data, non-vectorial data, other regularizers||slides (PDF)|
|Mar 6||missing data, nonlinear regression||slides (PDF)|
|Mar 8||robust regression, classification||slides (PDF)|
|Mar 13||model evaluation, large-scale model learning||slides (PDF)|
|Mar 15||project Q&A|
|Mar 20||project Q&A|
|Mar 22||project presentations|
|Apr 3||Introduction: Why do we build models?|
|Apr 5||Descriptive statistics, estimating probability distributions|
|Apr 24||Estimating error bars|
|Apr 26||Comparing distributions, measuring correlations|
|May 3||Covariance matrices and Principal Component Analysis (PCA)|
|May 8||Basic spectral estimation using FFT and linear filtering|
|May 10||K-means clustering|
|May 15||Independent component analysis, project Q&A|
|May 17||Project presentations|
To take a look at the additional Downloads, please click here. (you must be logged in!)