Beskjeder
Dear all, thx to everybody for heroic efforts with all projects and weekly exercises. We are very much impressed by what you have done throughout the semester. As we now approach the deadline for the last project (midnight December 18), we wanted to just remind you that you do, as always, have an extra day for final adjustments etc. You will not be penalized if you correct/improve/adjust etc your project during Friday.
But please, do upload by the deadline the link to your GitHub/Gitlab or similar repos that contain your codes and project. That makes it easier for us to not forget you when we set split the grading tasks.
Final grades will be available early January, our deadline (from MN-fak study admin) for submitting grades is January 9, three weeks after the deadline for p3. The feedback on p3 is normally less detailed than the feedbacks we give for p1 and p2.
Else, since we've had problems with Canvas registering correctly groups exerci...
Dear all, this is our last week with regular activities and today, Monday November 24, we will have the last lecture.?
Today we will try to wrap up our discussions of autoencoders with a link to the principal component analysis before we try to summarize what we have done this semester (second part of the session today).? On Tuesday and Wednesday we will have our last lab sessions.?
The last set of weekly exercises has a deadline on Friday this week. We hope you have enjoyed the semester. We have and it has been a great pleasure to get to know you all. We plan to have the feedback for the second project by the end of this week, and the deadline for project 3 is December 15 and we are aiming at having the final grades early January. We will also go through all approved weekly exercises by the end of next week.? Several of you have experienced (and we have as well) that not all weekly exercises are properly registered. We will send an email to all of you...
Dear all, this is our second last week (our last lecture is November 24, note error in time planner, this lecture is missing there).
We hope you had a great weekend. The plans this week are:
Plans for the lecture Monday 17 November, with video suggestions etc.
Recurrent neural networks, code examples and long-short-term memory
Autoencoders (last topic this semester), second lecture, see link below for this week's lecture notes
Last lecture: November 24, note error in time planner.
Lab sessions on Tuesday and Wednesday.
Work and Discussion of project 3
Last weekly exercise with deadline November 28, available from (early morning) Tuesday November 18.
Last lab sessions: November 25 and 26
Reading rand video recommendations on RNNs
These lecture notes at https://github.com/CompPhysics/MachineLearning/blob/master/doc/pub/week47/ipynb/week47.ipynb...
Dear all, welcome back to FYS-STK3155/4155. We hope you had a great weekend and that project 2 is close to its finalization. We wish you all the very best with the finalization of the project.?
Today's lecture continues with deep learning methods. We start now with our penultimate topic, namely recurrent neural networks (RNNs), which have served as a precursor to LLMs as we know them today. It is also a popular method for learning time series. After RNNs, our last topic is going to be autoencoders. These two deep learning methods will be the topic of the last three lectures on November 10, 17 and 24. November 24 is our last lecture (note error in the UiO schedule, the 24th is missing). Project 3 is also available and we assigned a tentative deadline to December 15.?
We will discuss project 3 during the various lab sessions this week. The tentative plan for this week is thus:
Plan for week 46
Material for the lecture on Monday No...
Dear all, welcome back to a new week. We hope you've had a great weekend.
The aim this week is to discuss convolutional neural networks (CNNs), with the basic mathematics, which parameters we need to deal with and how we can implement CNNs using either Tensorflow/Keras and/or PyTorch. The lecture notes this week contain examples thereof. These examples can for example be used in project 3 if you to plan to use CNNs. Rashcka's text contains a good documentation on how to use PyTorch for both NNs, CNNs and recurrent neural networks (topic next week).
These week there are no exercises, we will focus only on work on project 2. If you not yet received feedback on project 1, it should be there by the end of the day today, please apologize the delay to those who have not yet received feedback on p1.
This week our plans are as follows:
Material for the lecture on Monday November 3, 202...
Dear all, welcome back to a new exciting week!
This week we plan to wrap up our discussions from last week on how to solve differential equations with neural networks (first lecture). Thereafter we start discussing the whys and hows of convolutional neural networks (CNN) and parts of their mathematical foundations. Next week we will show how we can construct codes for CNNs (relevant for project 3) and how to deal with image classification. Thereafter, for our last weeks of the semester, we will focus on other deep learning methods such as recurrent neural networks (basis of LLMs and studies of timeseries) and finally autoencoders.
The exercises this week mimick those of week 39, that is getting started with the report for project 2.
Here's the detailed plan with reading suggestions plus videos.
Plan for week 44
Material for the lecture Monday October 27, 2025....
Dear all, we hope you have had a great weekend. Here follows a short update about the plans for the coming week.
Material for the lecture on Monday October 20, 2025.
Reminder from last week, see also lecture notes from week 42 at https://compphysics.github.io/MachineLearning/doc/LectureNotes/_build/html/week42.html as well as those from week 41, see see https://compphysics.github.io/MachineLearning/doc/LectureNotes/_build/html/week41.html.
Building our own Feed-forward Neural Network.
Coding examples using Tensorflow/Keras and Pytorch examples. The Pytorch examples are adapted from Rashcka's text, see chapters 11-13..
...
Dear all, welcome back to a new week and new exciting possibilities! We trust you had a restful and enjoyable weekend.
This week, both for the lectures and the lab sessions, the aim is to continue our discussions on how to build a feed forward neural network code (FFNN).
Neural networks are the basic building stone of almost all advanced deep learning methods, from the standard FFNN, via convolutional neural networks to generative methods and reinforcement learning as well. Mastering the basic building blocks is thus central to our understanding of most of the deep learning methods. Deep learning methods are the focus of the rest of the semester.
This week our focus is on
Lecture October 13, 2025
Building our own Feed-forward Neural Network and discussion of project 2
Project 2 is available at ...
Dear all, first of all thx so much for heroic efforts with project 1. We are truly impressed by what you have been doing. Keep up the good work and best wishes to you all with the finalization of project 1.
This week we start discussing how to actually develop a neural network code. This will be the topic for the second project. We will make the project available next week and discuss it in more detail during the lectures and the lab sessions. This week we plan to start with a simpler set of exercises where you implement the feed-forward part of a code for a neural network. The exercises for this week can then in turn be used as a basis for the code in project 2.
The plans this week are (see also links to various videos):
Material for the lecture on Monday October 6, 2025
Neural Networks, setting up the basic steps, from the simple perc...
Dear all, we hope you've had a great weekend.
Here are the updates and plans for this and the coming week.
Today we will continue our discussion of logistic regression that we started last week, with coding examples as well. We will repeat some of the essential elements and derivations. Logistic regression will serve as our stepping stone towards neural networks and deep learning methods. Next week we will devote our time to setting up a neural network code and we will also introduce automatic differentiation, which will allow us to compute gradients and derivatives for different cost functions, without having to encode directly the expressions for the derivatives.
The plans for this week, with some video recommendations, are:
Lecture Monday September 29, 2025
- Logistic regression and gradient descent, examples on how to code
- ...
Dear all, welcome back to FYS-STK and a new week. We hope you had a great weekend.
Here are the plans for this week.
For the lecture on Monday the 22nd, the plans are
Resampling techniques, Bootstrap and cross validation and bias-variance tradeoff
Logistic regression, our first classification encounter and a stepping stone towards neural networks
Readings and Videos, resampling methods
Raschka et al, pages 175-192
Hastie et al Chapter 7, here we recommend 7.1-7.5 and 7.10 (cross-validation) and 7.11 (bootstrap). See https://link.springer.com/book/10.1007/978-0-387-84858-7.
Dear all, the video from one of the lab sessions, where we discuss and derive the bias-variance tradeoff, is available at
It may be of relevance for the exercises this week and obviously project 1. Furthermore, the whiteboard notes for this week have been updated and you will find the derivation of the bias-variance tradeoff equations there as well, see https://github.com/CompPhysics/MachineLearning/blob/master/doc/HandWrittenNotes/2025/FYSSTKweek38.pdf
Finally, there was a typo in exercise 4a (this has been corrected now). There should only be a single target, as we should not resample targets.
These lines:
predictions = n...
Dear all, welcome back to a new exciting week. We hope you all have enjoyed and are still enjoying the weekend.
The plans this week are to start with a discussion of a statistical interpretation of OLS, Ridge and Lasso (to be continued next week as well).
This is relevant for the weekly exercises this week and the final part of project 1. We will also discuss the so-called Bias-Variance tradeoff and resampling methods like cross-validation and bootstrap. The videos listed below may also be helpful. Take a look at them before the lecture if you can. I am particularly fond of the Statquest videos of Josh Starmer, see https://statquest.org/
Material for the lecture on Monday September 15.
Statistical interpretation of OLS regression and other statistical properties
Resampling techniques, Bootstrap and cross validation and bias-variance tradeoff (this ma...
Dear all, welcome back to FYS-STK3155/4155 and a new exciting week! Our plans this week are
to discuss the family of gradient descent methods which we need to implement in the project (parts c-e, including Lasso regression).
Plain gradient descent (constant learning rate), reminder from last week with examples using OLS and Ridge
Improving gradient descent with momentum
Introducing stochastic gradient descent
More advanced updates of the learning rate: ADAgrad, RMSprop and ADAM
Readings and Videos:
Recommended: The textbook Goodfellow et al, Deep Learning, contains a good introduction to gradient descent, see sections 4.3-4.5 at https://www.deeplearningbook.org/contents/nume...
Dear all, project 1 (first version) is available from the folder https://github.com/CompPhysics/MachineLearning/tree/master/doc/Projects/2025/Project1 (either as pdf+latex or jupyter-notebook) and from the jupyter-book site https://compphysics.github.io/MachineLearning/doc/LectureNotes/_build/html/project1.html
We will discuss the project during the coming lab sessions.
Do not hesitate to ask in case you are in doubt.
Best wishes to you all.
Dear all, welcome back to a new week. We hope you've had a nice and relaxing weekend.
Here are the plans for the coming week.
We will discuss in more detail the mathematics of ordinary least squares, Ridge regression and Lasso regression, introduced at the end of the lecture last week. This is will be the material for the first lecture on Monday. Thereafter (second lecture) we will start discussing the numerical solution of the optimization problem using gradient methods, or what are normally called gradient descent methods.
Ordinary Least Squares and Ridge regression are methods where we have an analytical solution for the optimal parameters. For Lasso regression we need to solve the equations numerically. This is the standard situation in essentially all machine learning methods. Introducing gradient methods, we will thus also introduce the recipe for solving the equation for the Lasso regression...
Dear all, welcome back to FYS-STK3155/4155. We hope you've had a great weekend. This week we plan to continue our discussion of linear regression, with an emphasis on its derivation and links to mathematical interpretations. We plan also to start our discussion of Ridge and Lasso regression. The plans are
Brief repetition from last week
o Discussions of the equations for ordinary least squares (OLS)
o Discussion on how to prepare data and examples of applications of linear regression
o Mathematical interpretations of OLS
o Introduction of Ridge and Lasso regression
Reading recommendations:
The weekly lecture notes
Goodfellow, Bengio and Courville, Deep Learning, chapter 2 on linear algebra
Raschka et al on preprocessing of data, relevant...
If you are interested in finding team mates for projects and exercises, please fill in the form at https://docs.google.com/forms/d/1W57mA196ojFKxqW4-T6NsN0rx1BFUl-j8b4nQzrcG34/edit
First of all a warm welcome to you all.
Our first lecture is Monday August 18, 215pm-4pm.
The sessions on Tuesdays and Wednesdays last four hours for each group (four in total) and will include lectures in a flipped mode (promoting active learning) and work on exercises and projects. The sessions will begin with lectures and questions and answers about the material to be covered every week. There are four groups, Tuesdays 815am-12pm and 1215pm-4pm and Wednesdays 815am-12pm and 1215pm-4pm. Please sign up as soon as possible for one of the groups. Max capacity per group is 30-40 participants. Please select the group which fits you best.
The first week we start with simple linear regression, a repetition of linear algebra and elements of statistics needed for the course.
Note that there is no mandatory presence. All lectures can be accessed either in person or live via zoom at https://uio.zoom.us/my/mortenhj
...