Kursöversikt
Teachers
Course responsible and lecturer: Richard Johansson (richard.johansson@gu.se).
Assistant lecturers: Selpi, Vilhelm Verendel.
Teaching assistants: Chatrine Qwaider, Razan Ghzouli, Jin Guo, Natalia Jurczyńska.
Student representatives
TBA.
Assignments
Non-compulsory exercise: Introduction to machine learning in Python
Assignment 1: Reading a scientific paper in applied machine learning (deadline: February 1)
Assignment 2: Machine learning mini-project (deadlines: February 4, 11 and 15)
Assignment 3: Theory recap
Assignment 4: Classifier implementation
Assignment 5: Classifying images
Assignment 6: Machine learning meets the real world
Exercise questions
TBA.
Schedule
Date and time | Summary | Topics | Reading |
---|---|---|---|
Tue, Jan 22 13:15–15:00, HC1 |
Lecture [pdf] [video 1] [video 2] |
Course introduction. Basic ideas in machine learning. Decision trees. Introduction to scikit-learn. |
Scikit-learn: tutorial, decision trees. |
Thu, Jan 24 13-15 / 15-17, ED3582 |
Lab session |
|
|
Fri, Jan 25 13:15–15:00, HC1 |
Lecture |
Collecting and annotating data. |
|
Tue, Jan 29 13:15–15:00, HC1 |
Lecture |
Linear algebra recap. Linear classifiers and regression models. The perceptron and Widrow-Hoff algorithms. |
|
Thu, Jan 31 13-15 / 15-17, ED3582 |
Lab session |
Assignment 2: Machine learning mini-project (1) |
|
Fri, Feb 1 13:15–15:00, HC1 |
Lecture |
Feature encoding, preprocessing, selection. Hyperparameter tuning. |
|
Tue, Feb 5 |
|
||
Thu, Feb 7 13-15 / 15-17, ED3582 |
Lab session |
Assignment 2: Machine learning mini-project (2) |
|
Fri, Feb 8 13:15–15:00, HC1 |
Lecture |
Optimization and machine learning. Gradient descent. Regularized linear regression models. Introduction to PyTorch. |
|
Tue, Feb 12 13:15–15:00, HC1 |
Lecture |
Logistic regression and support vector classifiers. |
|
Thu, Feb 14 |
|
||
Fri, Feb 15 13:15–15:00, HA2 |
Lecture |
Evaluation methodology for machine learning systems. |
|
Tue, Feb 19 13:15–15:00, HC1 |
Lecture |
Ensembles and boosting. |
|
Thu, Feb 21 13-15 / 15-17, ED3582 |
Lab session |
Assignment 4: Classifier implementation |
|
Fri, Feb 22 13:15–15:00, HC1 |
Lecture |
Neural network introduction. Introduction to Keras. |
|
Tue, Feb 26 13:15–15:00, HC1 |
Lecture |
Convolutional neural networks. Introduction to neural networks for text, word embeddings. |
|
Thu, Feb 28 13-15 / 15-17, ED3582 |
Lab session |
Assignment 5: Classifying images (1) |
|
Fri, Mar 1 13:15–15:00, HC1 |
Lecture (Vilhelm Verendel) |
Ethical and legal issues. Fairness and bias. Explanations. Domain effects. |
|
Tue, Mar 5 13:15–15:00, HC1 |
Lecture |
Machine learning for sequential data. |
|
Thu, Mar 7 13-15 / 15-17, ED3582 |
Lab session |
Assignment 5: Classifying images (2) |
|
Fri, Mar 8 13:15–15:00, HC1 |
Lecture (Selpi) |
Overview of unsupervised learning. |
|
Tue, Mar 12 13-15 / 15-17, ED3582 |
Lecture |
Invited industry guest lecture. |
|
Thu, Mar 14 13-15 / 15-17, ED3582 |
Lab session |
(reserved lab slot) |
|
Fri, Mar 15 13:15–15:00, HC1 |
Exercise |
Course recap. Preparing for the final. |
|
mid-March | Take-home exam |
|
|
Kurssammanfattning:
Datum | Information | Sista inlämningsdatum |
---|---|---|