Add to watchlist
Back

 

17165-01 - Lecture: Machine Learning 8 CP

Semester spring semester 2021
Course frequency Every spring sem.
Lecturers Volker Roth (volker.roth@unibas.ch, Assessor)
Content Probabilities
Generative models for discrete data
Classification & regression: Frequentist & Bayesian approaches, model selection, sparse models
Neural networks: Feed-forward & recurrent topologies, encoder-decoder models, interpretability in deep learning models
Elements of statistical learning theory
Support Vector Machines and kernels, Gaussian processes
Mixture models, mixtures of experts
Linear latent variable models: Factor analysis, PCA, CCA
Non-linear latent variable models: Variational autoencoders, deep information bottlenecks
Learning objectives Understand the theoretical foundations of Machine Learning

Understand and apply practical learning algorithms: linear and generalized linear models for regression and classification, neural networks, Support Vector machines & kernel methods, mixture models & clustering.

Program in Python. PyTorch & Tensorflow
Bibliography https://mitpress.mit.edu/books/machine-learning-1
https://www.deeplearningbook.org/
Comments Target group: Master students
Weblink Course website

 

Admission requirements Basic knowledge and skills regarding pattern recognition, numerical analysis, and statistics
Course application Übung: https://courses.cs.unibas.ch
Language of instruction English
Use of digital media Online, mandatory
Course auditors welcome

 

Interval weekly
Date 02.03.2021 – 02.06.2021
Time Tuesday, 10.15-12.00 - Online Präsenz -
Wednesday, 14.15-16.00 - Online Präsenz -
Date Time Room
Tuesday 02.03.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 03.03.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 09.03.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 10.03.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 16.03.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 17.03.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 23.03.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 24.03.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 30.03.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 31.03.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 06.04.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 07.04.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 13.04.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 14.04.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 20.04.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 21.04.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 27.04.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 28.04.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 04.05.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 05.05.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 11.05.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 12.05.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 18.05.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 19.05.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 25.05.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 26.05.2021 14.15-16.00 - Online Präsenz -, --
Tuesday 01.06.2021 10.15-12.00 - Online Präsenz -, --
Wednesday 02.06.2021 14.15-16.00 - Online Präsenz -, --
Modules Doctorate Computer Science: Recommendations (PhD subject Computer Science)
Kernfächer und Seminar (Master's Studies: Computational Biology and Bioinformatics)
Modul: Concepts of Machine Intelligence (Master's degree subject Computer Science)
Module: Applications of Distributed Systems (Master's Studies: Computer Science)
Module: Concepts of Machine Intelligence (Master's Studies: Computer Science)
Module: Interdisciplinary and Transfer of Knowledge (Master's Studies: Actuarial Science)
Assessment format continuous assessment
Assessment details Oral exam
Expected Date: 23/24/25 June 2021, online
Admission to the examination: handing in "reasonable" solutions to >70% of the exercises
Assessment registration/deregistration Reg./dereg.: course registr./cancel registr. via MOnA
Repeat examination no repeat examination
Scale 1-6 0,5
Repeated registration as often as necessary
Responsible faculty Faculty of Science, studiendekanat-philnat@unibas.ch
Offered by Fachbereich Informatik

Back