Computer Engineering MA, Neural Networks and Deep Learning, 6 credits

Aim

The student should understanding modern machine learning techniques. The student should develop skills in finding interesting features, building graphic and deep learning models by using Python. The student should show an ability to apply the skills in a small project in an real-world business or engineering application area.

Course objectives

Upon completion of the course the student should be able to:
- describe ensemble methods, graphic models and deep learning,
- apply these techniques in a real-world business or engineering application area,
- implement several types of machine learning methods and modify them,
- critically evaluate the methods’ applicability in new contexts.

Content

• Multilayer perceptron
• Convolutional neural network
• Recurrent neural network
• Regularization for deep learning
• Optimization for model training
• Labs for deep learning with Python
• Project

Entry requirements

Computer Engineering BA (AB), including Databases, Modeling and Implementation, 6 credits. Computer Engineering MA, Data Mining, 6 credits. Mathematics BA (A), 30 credits, including Mathematical Statistics, 6 credits.

Total previous studies 120 credits.

Selection rules and procedures

The selection process is in accordance with the Higher Education Ordinance and the local order of admission.

Teaching form

The course may be offered as a campus course or as a web-based distance course. The student time commitment is estimated to about 160 hours.

Examination form

L101: Laboratory exercise, 1 Credits
Grade scale: Two-grade scale

P101: Project with written report, 2 Credits
Grade scale: Two-grade scale

T101: Written Exam, 3 Credits
Grade scale: Seven-grade scale, A-F o Fx

The final grade is based on combined exam and project assessment.

Grading criteria for the subject can be found at www.miun.se/gradingcriteria.

The examiner has the right to offer alternative examination arrangements to students who have been granted the right to special support by Mid Sweden University’s disabilities adviser.

If examination on campus cannot be conducted according to decision by the vice-chancellor, or whom he delegated the right to, the following applies: Written Exam T101, will be replaced with two parts, online examination and follow-up. Within three weeks of the online examination, a selection of students will be contacted and asked questions regarding the examination. The follow-up consists of questions concerning the execution of the on-line exam and the answers that the student have submitted.

Examination restrictions

Students registered on this version of the syllabus have the right to be examined 3 times within 1 year according to specified examination forms. After that, the examination form applies according to the most recent version of the syllabus.

Grading system

Seven-grade scale, A-F o Fx