IKT450 Deep Neural Networks
- ECTS Credits:
- 7.5
- Responsible department:
- Faculty of Engineering and Science
- Course Leader:
- Morten Goodwin
- Lecture Semester:
- Autumn
- Teaching language:
- English
- Duration:
- 1 term
The course is connected to the following study programs
- Master's Programme in Information and Communication Technology
- Artificial Intelligence, 5-year master programme
Teaching language
EnglishCourse contents
The course covers theoretical and practical aspects of neural networks:
- fundamentals of neural networks including feed-forward models, optimizers, and training algorithms (e.g., backpropagation),
- neural network architectures including deep learning models, convolutional neural networks, recurrent neural networks, autoencoders, and generative adversarial networks, and
- working end-to-end pipelines including performance evaluation, detecting overfitting, underfitting, and data defects.
Learning outcomes
In this course, the students will learn the foundations of neural networks and deep learning. They will, at course completion, be able to build and train feed-forward and recurrent neural models, understand the critical parameters in neural architectures, and understand when to apply different models. The students will also learn the theoretical foundation of the models, types of layers, and optimizers, and learn how to design, implement, and analyze advanced shallow and deep neural networks. They will gain practical programming experience with deep neural networks highly relevant to the industry.
Teaching methods
Combination of lectures, assignments, paper studies, lab, and report writing. The tasks are done individually or in small groups with group supervision.
The work load for the average student is approximately 200 hours.
Evaluation
The study programme manager, in consultation with the student representative, decides the method of evaluation and whether the courses will have a midterm- or end of term evaluation, see also the Quality System, section 4.1. Information about evaluation method for the course will be posted on Canvas.
Offered as Single Standing Module
Yes, subject to availability.
Assessment methods and criteria
Graded portfolio assessment. Information about the content of the portfolio will be given in LMS by the start of the semester.