Syllabus for Deep Learning for Image Analysis
Djup maskininlärning för bildanalys
- 7.5 credits
- Course code: 1MD120
- Education cycle: Second cycle
Main field(s) of study and in-depth level:
Image Analysis and Machine Learning A1F,
Computer Science A1F
Explanation of codes
The code indicates the education cycle and in-depth level of the course in relation to other courses within the same main field of study according to the requirements for general degrees:
- G1N: has only upper-secondary level entry requirements
- G1F: has less than 60 credits in first-cycle course/s as entry requirements
- G1E: contains specially designed degree project for Higher Education Diploma
- G2F: has at least 60 credits in first-cycle course/s as entry requirements
- G2E: has at least 60 credits in first-cycle course/s as entry requirements, contains degree project for Bachelor of Arts/Bachelor of Science
- GXX: in-depth level of the course cannot be classified
- A1N: has only first-cycle course/s as entry requirements
- A1F: has second-cycle course/s as entry requirements
- A1E: contains degree project for Master of Arts/Master of Science (60 credits)
- A2E: contains degree project for Master of Arts/Master of Science (120 credits)
- AXX: in-depth level of the course cannot be classified
- Grading system: Fail (U), Pass (3), Pass with credit (4), Pass with distinction (5)
- Established: 2020-02-27
- Established by:
- Revised: 2020-10-08
- Revised by: The Faculty Board of Science and Technology
- Applies from: Autumn 2021
120 credits including Statistical Machine Learning, calculus of several variables, a second programming course and Introduction to Image Analysis or Computer-Assisted Image Analysis. Proficiency in English equivalent to the Swedish upper secondary course English 6.
- Responsible department: Department of Information Technology
After passing the course the student should be able to
- describe and use backpropagation together with gradient descent and stochastic gradient descent to optimize a model;
- implement, from the ground up, a fully interconnected multilayer neural network;
- explain under- and over-fitting and what can be done to avoid these;
- describe and use different kinds of regularization techniques;
- use modern environments for deep machine learning to solve practical image processing and image analysis problems;
- describe and use deep convolutional networks for image classification, object detection and image segmentation;
- critically analyse research in the main field, assess its possibilities and limitations.
Deep learning for visual data. Data-driven image classification, linear classification, activation functions, various cost functions, gradient-based optimization with backpropagation. Convolutional neural networks (CNN) and methods for training them, transfer learning and data augmentation. Different architectures and applications in image analysis (classification, detection, segmentation). Visualization and understanding of convolutional neural networks. Generative Adversarial Networks (GANs). Possibilities and limitations with deep learning.
Lectures, assignments, computer exercises and project work in groups.
Written exam (3 credits), approved assignments and laboratory work, oral and written presentation of project work (4.5 credits).
If there are special reasons for doing so, an examiner may make an exception from the method of assessment indicated and allow a student to be assessed by another method. An example of special reasons might be a certificate regarding special pedagogical support from the disability coordinator of the university.
- Latest syllabus (applies from Autumn 2021)
- Previous syllabus (applies from Autumn 2020)
The reading list is missing. For further information, please contact the responsible department.