Statistical Deep Learning
The course treats basic as well as modern concepts of statistical learning in terms of artificial neural networks (deep learning), with applications in statistical data analysis.
Topics treated include feedforward networks, regularization and optimization of networks with many layers, convolutional networks, recurrent networks and validation methods. In addition, mathematical interpretations of networks are given, such as nonlinear regression with different link functions for the outcome variable. The course includes some of the following topics; autoencoders, representation learning, deep generative methods, and information theoretic concepts of deep learning.
Overlapping courses
This course overlaps with the courses Deep Learning in Data Science (DA7064) and Machine Learning (DA7063), which were given for the last time in the spring 2022. Therefore the course should not be included in the same degree as DA7064, or in the same degree as DA7063 if the degree also contains Statistical Learning (MT7038).
Information for admitted students autumn 2024
Congratulations! You have been admitted at Stockholm University and we hope that you will enjoy your studies with us.
In order to ensure that your studies begin as smoothly as possible we have compiled a short checklist for the beginning of the semester.
Follow the instructions on whether you have to reply to your offer or not.
universityadmissions.se
Checklist for admitted students
-
Activate your university account
The first step in being able to register and gain access to all the university's IT services.
-
Register at your department
Registration can be done in different ways. Read the instructions from your department below.
-
Read all the information on this page
Here you will find what you need to know before your course or programme starts.
IMPORTANT
Your seat may be withdrawn if you do not register according to the instructions provided by your department.
Information from your department
On this page you will shortly find information on registration, learning platform, etc.
Welcome activities
Stockholm University organises a series of welcome activities that stretch over a few weeks at the beginning of each semester. The programme is voluntary (attendance is optional) and includes Arrival Service at the airport and an Orientation Day, see more details about these events below.
Your department may also organise activities for welcoming international students. More information will be provided by your specific department.
Find your way on campus
Stockholm University's main campus is in the Frescati area, north of the city centre. While most of our departments and offices are located here, there are also campus areas in other parts of the city.
Read more
For new international students
Topics treated include feedforward networks, regularization and optimization of networks with many layers, convolutional networks, recurrent networks and validation methods. In addition, mathematical interpretations of networks are given, such as nonlinear regression with different link functions for the outcome variable. The course includes some of the following topics; autoencoders, representation learning, deep generative methods, and information theoretic concepts of deep learning.
Overlapping courses
This course overlaps with the courses Deep Learning in Data Science (DA7064) and Machine Learning (DA7063), which were given for the last time in the spring 2022. Therefore the course should not be included in the same degree as DA7064, or in the same degree as DA7063 if the degree also contains Statistical Learning (MT7038).
-
Course structure
The course consists of two parts: theory and hand-in assignments.
Teaching format
Instruction is given in the form of lectures, exercise sessions and supervision.
Assessment
The course is assessed through a written exam and home assignments.
Examiner
A list of examiners can be found on
-
Schedule
The schedule will be available no later than one month before the start of the course. We do not recommend print-outs as changes can occur. At the start of the course, your department will advise where you can find your schedule during the course. -
Course literature
Note that the course literature can be changed up to two months before the start of the course.
Goodfellow, Bengio, Courville: Deep Learning. MIT Press.
-
More information
New student
During your studiesCourse web
We do not use Athena, you can find our course webpages on kurser.math.su.se.
-
Contact