New Technologies (5 cr)

Evaluation scale

H-5

Content scheduling

The applied artificial intelligence course offers students a specialization in artificial intelligence (AI) for engineering application domains. This course requires a strong background in understanding the theoretical foundations of AI, together with an understanding of mathematics and computer engineering applications for intelligent networks, autonomous robotics, computer vision, and biomedical engineering. Theoretical and technical knowledge is combined with hands-on experience in implementing practical applications.

Objective

After completing the course, the student is able to:
-understand new IoT systems
-learn by themselves advanced IoT architectures and solutions
-understand differences and possibilities in new wireless IoT systems

Content

-Recent solutions for IoT
-Wireless IoT solutions, differences and possibilities

Materials

Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow, Book by Aurelien Geron
Deep Learning with Python, Book by François Chollet
Neural Networks and Deep Learning, Book by Michael Nielsen
Deep Learning, Book by Ian Goodfellow, Yoshua Bengio, and Aaron Courville

Teaching methods

Lectures (contact teaching)
Hands-on materials
Project work
Self Study Materials

Exam schedules

The final evaluation is based on individual students' project work assigned during the lifecycle of the course.

Student workload

2 Lecture Days, approximately 4h/day, have been planned for this course. Self-study materials will be given as well.

Evaluation methods and criteria

By the end of this course, students will:
Obtain practical and technological skills including machine learning, optimization, neural networks, data processing, and advanced AI algorithms

Possess knowledge of state-of-the-art modern topics in artificial intelligence, including Regression, Classification, support vector machines, neural networks, deep networks, and basics of reinforcement learning

Learn a blend of hardware, software, and data analytics skills to support the design and development of AI applications in various engineering domains

Failed (0)

The final evaluation will be based on the student's performance and final project work including a written report. The evaluation metric for this course will be based on Pass / Fail.

Further information

This is an advanced course and requires students sufficient background in Machine Learning, or at least basics of data analysis and probability concept. Python programming skills are essential for this course.