mhjensen
12 KiB
12 KiB
Teaching schedule with links to material
This course will be delivered in a hybrid mode, with online lectures and on site or online laboratory sessions.
- Four lectures per week, Fall semester, 10 ECTS. The lectures are in person but will be recorded and linked to this site and the official University of Oslo website for the course;
- Two hours of laboratory sessions for work on computational projects and exercises for each group. There will also be fully digital laboratory sessions for those who cannot attend;
- Three projects which are graded and count 1/3 each of the final grade. The deadlines for the projects are October 11 for project 1, November 15 for project 2 and December 13 for project 3.
- A selected number of weekly assignments;
- The course is part of the CS Master of Science program, but is open to other bachelor and Master of Science students at the University of Oslo;
- The course is offered as a FYS-MAT4155 (Master of Science level) and a FYS-MAT3155 (senior undergraduate) course;
- Videos of teaching material are available via the links at https://compphysics.github.io/MachineLearning/doc/web/course.html;
- Weekly emails with summary of activities will be mailed to all participants;
Weekly Schedule
For the reading assignments we use the following abbreviations:
- GBC: Goodfellow, Bengio, and Courville, Deep Learning
- CMB: Christopher M. Bishop, Pattern Recognition and Machine Learning
- HTF: Hastie, Tibshirani, and Friedman, The Elements of Statistical Learning
- AG: Aurelien Geron, Hands‑On Machine Learning with Scikit‑Learn and TensorFlow
Week 34 August 23-27
-
Lab Wednesday: Introduction to software and repetition of Python Programming
-
Lecture Thursday: Introduction to the course, what is Machine Learning and introduction to Linear Regression.
-
Video of Lecture August 26, 2021 at https://www.uio.no/studier/emner/matnat/fys/FYS-STK4155/h21/forelesningsvideoer/LectureThursdayAugust26.mp4?vrtx=view-as-webpage
-
Lecture Friday: Basics of Linear Regression
-
Video of Lecture August 27, 2021 at https://www.uio.no/studier/emner/matnat/fys/FYS-STK4155/h21/forelesningsvideoer/LectureThursdayAugust27.mp4?vrtx=view-as-webpage
-
Reading recommendations:
- Refresh linear algebra, GBC chapters 1 and 2.
- CMB sections 1.1 and 3.1.
- HTF chapters 2 and 3.
- See lecture notes for week 34 at https://compphysics.github.io/MachineLearning/doc/web/course.html
Week 35 August 30-September 3
-
Lab Wednesday: Work on exercises 1-3 for week 35
-
Thursday: Review of ordinary Least Squares with applications and discussion of Ridge Regression and Singular Value Decomposition
-
Video of lecture Thursday at https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureSeptember2.mp4?vrtx=view-as-webpage.
-
Friday: Analysis of Ridge and Lasso Regression and links with Singular Value Decomposition
-
Video of lecture Friday at https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureSeptember3.mp4?vrtx=view-as-webpage
-
Reading recommendations:
- See lecture notes for week 35 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- HTF chapter 3. GBC chapters 1 and and sections 3.1-3.11 and 5.1
- CMB sections 1.1 and 3.1
Week 36 September 6-10
-
Lab Wednesday: Exercises 1 and 2 from week 36
-
Lecture Thursday: Summary from last week on SVD, Statistics, probability theory and linear regression
-
Video of Lecture https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureSeptember9.mp4?vrtx=view-as-webpage
-
Friday: Linear Regression and links with Statistics, Resampling methods and presentation of first project.
-
Video of Lecture at https://www.uio.no/studier/emner/matnat/fys/FYS-STK4155/h21/forelesningsvideoer/LectureSeptember10.mp4?vrtx=view-as-webpage
-
Reading recommendations:
- Lectures on Regression for week 36 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- Bishop 1.1, 1.2, 2.1, 2.2, 2.3 and 3.1
- Hastie et al chapter 3
Week 37 September 13-17
- Lab Wednesday: Work on Project 1
- Lecture Thursday: Resampling methods, cross-validation and Bootstrap
- Thursday September 16: Summary of Ridge and Lasso with examples and start resampling techniques
- Video of Lecture, first part at https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureSeptember16Firstpart.mp4?vrtx=view-as-webpage"
- Video of Lecture, second part at https://www.uio.no/studier/emner/matnat/fys/FYS-STK3155/h21/forelesningsvideoer/LectureSeptember16SecondPart.mp4?vrtx=view-as-webpage
- Thursday September 16: Summary of Ridge and Lasso with examples and start resampling techniques
- Lecture Friday: More on Resampling methods and summary of linear regression
- Reading recommendations:
- Lectures on Resampling methods for week 37 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- Bishop 1.3 (cross-validation) and 3.2 (bias-variance tradeoff)
- Hastie et al Chapter 7, here we recommend 7.1-7.5 and 7.10 (cross-validation) and 7.11 (bootstrap)
- Goodfellow et al discuss some of these topics in sections 5.2-5.5.
Week 38 September 20-24
- Lab Wednesday: Work on Project 1
- Lecture Thursday: Classification problems and Logistic Regression, from binary cases to several categories
- Lecture Friday: Logistic Regression and gradient optimization
- Reading recommendations:
- See lecture notes for week 38 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- Bishop 4.1, 4.2 and 4.3. Not all the material is relevant or will be covered. Section 4.3 is the most relevant, but 4.1 and 4.2 give interesting background readings for logistic regression
- Hastie et al 4.1, 4.2 and 4.3 on logistic regression
- For a good discussion on gradient methods, see Goodfellow et al section 4.3-4.5 and chapter 8. We will come back to the latter chapter in our discussion of Neural networks as well.
Week 39 September 27- October 1
- Lab Wednesday: Work on Project 1
- Lecture Thursday: Gradient Optimization methods
- Lecture Friday: Gradient methods
- Reading recommendations:
- See lecture notes for week 39 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- For a good discussion on gradient methods, see Goodfellow et al section 4.3-4.5 and chapter 8. We will come back to the latter chapter in our discussion of Neural networks as well.
Week 40 October 4-8
- Lab Wednesday: Wrap up project 1
- Lecture Thursday: Stochastic gradient descent, automatic differentiation and start discussion of feed-forward Neural Network code for regression and classification
- Lecture Friday: Deep Learning and Neural Networks: the back propagation algorithm
- Reading recommendations:
- See lecture notes for week 40 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- For neural networks we recommend Goodfellow et al chapters 6 and 7 and Bishop 5.1-5.4
- For stochastic gradient descent we recommend Goodfellow et al chapter 8
Week 41 October 11-15
- Lab Wednesday: Work on project 2
- Lecture Thursday: Deep learning and Neural Networks, developing a code for Neural Networks
- Lecture Friday: Tensorflow and the mathematics of neural network
- Reading recommendations:
- See lecture notes for week 41 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- For neural networks we recommend Goodfellow et al chapters 6 and 7. For CNNs, see Goodfellow et al chapter 9. chapter 11 and 12 on practicalities and applications
Week 42 October 18-22
- Lab Wednesday: Work on project 2
- Lecture Thursday: Solving differential equations with neural networks and start Convolutional Neural Networks and classification problems
- Lecture Friday: Convolutional Neural Networks and classification problems
- Reading recommendations:
- See lecture notes for week 42 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- For neural networks we recommend Goodfellow et al chapters 6 and 7. For CNNs, see Goodfellow et al chapter 9. See also chapter 11 and 12 on practicalities and applications
Week 43 October 25-29
- Lab Wednesday: Work on project 2
- Lecture Thursday: Recurrent Neural Networks
- Lecture Friday: Recurrent Neural Networks and principal component analysis (PCA)
- Reading recommendations:
- See lecture notes for week 43 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- For RNNs, see Goodfellow et al chapter 10 and discussions in chapter 11 and 12 on practicalities and applications
- For PCA see lecture notes (jupyter book) chapter 11 and also chapter 12 on clustering. Geron's chapter 8 is also a good read.
Week 44 November 1-5
- Lab Wednesday: Work on project 2
- Lecture Thursday: Decision trees, classification and regression
- Lecture Friday: Decision trees, basic algorithms
- Reading recommendations:
- See lecture notes for week 44 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- Hastie et al sections 9.1 and 9.2
Week 45 November 8-12
- Lab Wednesday: Work on project 2 and start project 3
- Lecture Thursday: Ensemble methods, bagging and random forests
- Lecture Friday: Boosting and gradient boosting
- Reading recommendations:
- See lecture notes for week 45 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- Hastie et al chapter 10
Week 46 November 15-19
- Lab Wednesday: Work on project 3
- Lecture Thursday: Support Vector machines
- Lecture Friday: Support Vector machines
- Reading recommendations:
- See lecture notes for week 46 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
- Hastie et al chapter 12
Week 47 November 22-26
- Lab Wednesday: Work on project 3
- Lecture Thursday: Unsupervised Learning, Principal Component Analysis (PCA)
- Lecture Friday: Unsupervised Learning and PCA, k-means and Clustering
- Reading recommendations:
- See lecture notes for week 47 at https://compphysics.github.io/MachineLearning/doc/web/course.html.
Week 48 November 29- December 2
- Lab Wednesday: Work on project 3
- Lecture Thursday: Unsupervised Learning and Clustering
- Lecture Friday: Summary of course
- Reading recommendations:
- See lecture notes for week 48 at https://compphysics.github.io/MachineLearning/doc/web/course.html.