Introduction to Machine Learning 2019

Introduction to Machine Learning

The course will introduce the foundations of learning and making predictions from data. We will study basic concepts such as trading goodness of fit and model complexity. We will discuss important machine learning algorithms used in practice, and provide hands-on experience in a course project. VVZ Information is available here.
News
  • The review session slides can be found here: Slides
  • ANNOUNCEMENT: There are no lectures in the week 27.5-31.5. The lecture on 22 May was the last one. Tutorial carry as normal in the week 27-31 May.
  • The exam will take place on a computer. Please inform us about any special request regarding a disability.
  • In the first week’s tutorial sessions (Mon, Tue, Wed, Fri), we will offer a review session of required background material for the course. This will include a short recap of linear algebra, multivariate analysis and probability theory.
  • For programming background, we recommend knowing Python. For those without experience in it, check one of the excellent tutorials Python Tutorial I , Python Tutorial II , Python Tutorial III
  • For the mathematical background check the excellent resource: Mathematics for Machine Learning Online version
  • Please attend the tutorials according to last name: A-C: Mon 15-17,HG D 1.2 D-H: Tue 15-17,HG D 1.2 I-M: Wed 15-17,CAB G 11 N-Z: Fri 13-15, ML D 28
  • The files are password protected. To obtain the password you need to be inside the ETH network and click here. To establish a VPN connection click here.
FAQ
  • 1. If this course is compolsury for your study program (Kernfach), you are able to register irrespective of the waiting list. Please allow some time for the transfer from the waiting list.
  • 2. PhD students are required to obtain a passing grade in the course (4.0 or higher based on project and exam as detailed in the course catalog) to gain credit points.
  • 3. If you have a significant clash with other courses, and you cannot attend the assigned tutorial slot, you can attend other session, but first give seating to other students.
  • 4. The project is a mandatory part of the examination. Without achieving a passing grade (4), you are not allowed to sit the final examination.
  • 5. Distance examination is allowed but you need to file an official request via study administration. We do not handle these requests.
  • 6. Attendance at Tutorials and Lectures is not mandatory.
    Syllabus
    Date Topics Tutorial HW Solutions
    Tue 19.2. Introduction Tutorial I Homework 1 -
    Wed 20.2. Regression - - -
    Tue 26.2. Model Selection Tutorial II & Script - Solutions 1
    Wed 27.2 Cross Validation - - -
    Tue 5.3 Classification Tutorial III Homework 2
    Wed 6.3 Feature Selection
    Tue 12.3 Kernels Tutorial IV Solution 2
    Wed 13.3 Kernels II
    Tue 19.3 Kernels III Tutorial V Homework 3
    Wed 20.3 Class Imbalance
    Tue 26.3 Neural Networks Tutorial VI Solution 3
    Wed 27.3 Neural Networks II
    Tue 2.4 Neural Networks III Tutorial VII & Demo Homework 4
    Wed 3.4 Neural Networks IV
    Tue 9.4 Clustering Tutorial VIII Solution 4
    Wed 10.4 Dimensionality Reduction
    Tue 16.4 Dimensionality Reduction II Tutorial IX Homework 5
    Wed 17.4 Probabilistic Modeling
    Tue 30.4 Logistic Regression Tutorial X Solution 5
    Wed 1.5 No Class
    Tue 7.5 Decision Theory Tutorial XI Homework 6
    Wed 8.5 Generative Modeling
    Tue 14.5 Generative Modeling II Tutorial XII Solution 6
    Wed 15.5 GMMs
    Tue 21.5 GMMs II Tutorial XIII Homework 7
    Wed 22.5 GANs
    Tue 28.5 No Class Tutorial XIV Solution 7
    Wed 29.5 No Class
    • Video Lectures
    The video recordings of the lectures are available at the ETH Videoportal.
    Contact
    Instructors Prof. Andreas Krause
    Head TA Mojmir Mutny
    Assistants Andisheh Amrollahi, Mohammad Karimi, Prashanth Chandran, Joanna Ficek, Vincent Fortuin,Gürel Nezihe Merve, Harun Mustafa, Jingwei Tang, Kjong Lehmann, Natalie Davidson, Olga Mineeva, Laurie Prelot, Stefan Stark, Johannes Kirschner, Matteo Turchetta, Sebastian Curi, Max Paulus, Phillipe Wenk, Ilja Bogunovic, Aytunc Sahin, Kfir Levy, Anastasiia Makarova
    Piazza If you have any questions, please use the Piazza Course Forum.
    Mailing List Please use the Piazza Forum for questions regrading course material, organisation and projects. If this does not work for your request, you can send an email to responsible person from your ethz.ch address (expect longer response interval).
    Lectures
    Tue 13-15 HG E 7 HG E 3 and 5 (via video)
    Wed 13-15 HG E 7 HG E 3 and 5 (via video)
    Tutorials
    tutorial Room
    A-C: Mon 15-17 HG D 1.2
    D-H: Tue 15-17 HG D 1.2
    I-M: Wed 15-17 CAB G 11
    N-Z: Fri 13-15 ML D 28
    Home Problems
    Homeworks are not graded and not corrected. They are just for you to practice concepts. The problems are published bi-weekly (solutions follow one week after).
    Project
    Please find all information about the project here.
    Demos
    The Demo’s are based on jupyter notebook (with python 3). Please look at this intro for installing and running instructions. Helper files: (Please download them and save them on same directory as the demos). zipped helper files (Updated 22.3.2018) Demos:
    Performance Assessment
    70% session examination, 30% project; the final grade will be calculated as weighted average of both these elements. As a compulsory continuous performance assessment task, the project must be passed on its own. The exam might take place at a computer. The practical projects are an integral part (60 hours of work, 2 credits) of the course. Participation is mandatory. Failing the project results in a failing grade for the overall examination of Introduction to Machine Learning (252-0220-00L). Students who do not pass the project are required to de-register from the exam and will otherwise be treated as a no show.
    For the final exam, you can bring two A4-pages (i.e. one A4-sheet of paper), either handwritten or 11 point minimum font size. No calculators or other aids are allowed.

    Previous Exams:
    Exam 2015
    Exam 2016
    Exam 2017
    Text Books
    • Marc Peter Deisenroth, A Aldo Faisal, and Cheng Soon Ong Mathematics for Machine Learning Online version
    • K. Murphy. Machine Learning: a Probabilistic Perspective. MIT Press 2012
    • C. Bishop. Pattern Recognition and Machine Learning. Springer, 2007 (optional)
    • T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning: Data Mining, Inference and Prediction. Springer, 2001. Available online
    • L. Wasserman. All of Statistics: A Concise Course in Statistical Inference. Springer, 2004.