A solution to exam is now available here

A solution set to the trial exam is now available on the course web page.

We will provide zoom meetings on Thursday June 2 11.15-12.00 and Friday June 3 12.15-13.00 where you can ask questions about trial exams or other things related to the exam. There will be no recording of these sessions.

Zoom links:

• Thursday June 2:  https://uio.zoom.us/j/62060619742
• Friday June 3: https://uio.zoom.us/j/62016482180?pwd=Q1Z0LzFBMkp0V0lzTW1xQVljdEY1Zz09

Regarding the exam:

• The set will contain many pages, but don't be afraid, a lot of this are plots and outputs from different models. 
...

A trial exam is now available at this link.

This trial exam is much larger than an ordinary exam but should cover most of the curriculum. You can work on this on the plenary sessions on the Mondays to follow, and we will go through the solutions in the lecture times.

In the proposed help file for compulsory exercise 2, there was a typo in the logistic function in the help listing for (g).

It should of course have been 

  1/(1+exp(-as.numeric(output))) there.

In case you have not corrected this yourself, the points won't be subtracted for (g) provided that you have shown an attempt to work on the problem. But great if you have noticed the error and fixed it in your assignment!

There will be no lecture on May 5 to allow the students to concentrate on submitting the 2nd assignment.

Some of you have got some problems with question e.

First: The knn_mi function only performs the calculation for ONE prediction point at a time. Therefore, there is a need for a for loop in this case. 

Second: Predicting the i-th test observation can be performed by the command

pred.knn[i] = knn_mi(Xptr[Xtr$X==1,1:2],Xptr[Xtr$X==0,1:2],nn=3,as.matrix(Xpte[i,1:2]))>0.5

Note in particular the use of as.matrix. Without this, the call can crash.

Third: The for loop can be somewhat time-consuming. This will in particular be problematic when performing predictions based on Xnew. A possibility here is to use only the 5000, say, rows of Xnew.

Geir

The plenary session today Monday April 4 is unfortunately cancelled due to illness.

Due to technical issues the recordings 

Forelesningsopptak - 18.02.22

and 

Forelesningsopptak - 24.02.22

Have no sound.

For Forelesningsopptak - 18.02.22, one can watch similar lectures on LDA and QDA from last year 
part1

part2

part3

For week 8, two hours of lectures will be given on Monday 21.02 whilst exercises will be given on Friday 25.02 instead!

The first compulsory assignment is now available, see under Exercises on the course web page.

Due to a fire in VB on Wednesday, the building is closed today. The lecture today will therefore be on zoom, link  https://uio.zoom.us/j/62860580032 (Links to an external site.)

The lecture will also be recorded.

Geir

We are happy to announce that the lectures will be physical on campus! In addition, the lectures will be recorded so that those who for different reasons are not able to attend the lectures still can follow these digital. These will however only be available after the lectures are finished.

Due to that the Covid-19 disease still is around us, we ask all students to

• Use face masks indoors if the distance requirements canot be met
• Adhere to the rules on distance in the auditoriums
• Avoid congestion when entering / leaving auditoriums
• If possible, travel collectively to / from Blindern outside rush hours
• Choose a digital teaching offer if you suspect that you in the recent past have been exposed to coronavirus, e.g. at a slightly loose party.
• Follow the authority's general infection control advice