Schedule: 09.09.2019 - 09.12.2019
Contact information for the course (applies in this implementation):
Leo Kärkkäinen (leo.karkkainen at aalto.fi)
I am available in general at Aalto on Thursdays and Fridays. I will be available for answering questions on Thursdays 11:00 - 11:30 at F304, Otakaari 3.
Christabella Irwanta (christabella.Irwanta at aalto.fi) and Ruslan Lagashkin ( lagashkinruslan at gmail.com)
Teaching Period (valid 01.08.2018-31.07.2020):
I-II 2018-2019 (autumn)
Learning Outcomes (valid 01.08.2018-31.07.2020):
After the course, the student
- can explain the fundamentals of neural networks function.
- is able to construct, design, implement and run a deep learning based AI analysis project in medical domain.
- has the skills to select and utilize and the tools for applying AI for the different use cases needed for medical applications.
- is able to identify and develop the data sets that provide the best results.
Content (valid 01.08.2018-31.07.2020):
The course will contain the basics in deep learning, introduce the student how machine learning is used in different medical domains, and what technologies are appropriate in different use cases. The work has mathematical and programming exercises, and a project for designing and teaching a neural network for a medical use case.
Details on the course content (applies in this implementation):
Lectures Mondays and Exercises on Fridays 8-10 am at TU6 (1199), TUAS, Maarintie 8, Exercises Fridays
- Lecture 1: What is currently possible with AI? Selection of project work topics.
- Lecture 2: Introduction to probability. Basics and what is needed for the course.
- Lecture 3: Machine learning. Unsupervised, supervised, and reinforcement learning
- Lecture 4: Neural networks and medical data, legislation and ethics in use of AI. Data augmentation
- Lecture 5: Training of networks, back-propagation, stochastic gradient descent (SGD). Models of data with spatial, (translation) symmetries. Convolutional neural networks (CNNs). Medical imaging, object classification
- Lecture 6: Models of data with temporal symmetries. Recurrent neural networks.
Physiological signals, like ECG and BCG. Modeling the cardiovascular system.
- Lecture 7: Autoencoders, predicting the future, and de-noising signals. Generative adversarial networks (GANs)
- Lecture 8: Natural Language Processing. Attention models. Generating text
- Lecture 9: AI in embedded systems. Compressing deep neural networks. HW for AI.
- Lecture 10: Challenges in using AI in health. Adversarial examples. Differential privacy
- Lecture 11: What could we expect of the future?
- Lectures 12 - 13 and Exercise 13: Project work reports
- Lecture 14: Exam
Assessment Methods and Criteria (valid 01.08.2018-31.07.2020):
Project work, exercises, and final examination
Elaboration of the evaluation criteria and methods, and acquainting students with the evaluation (applies in this implementation):
Each week we will have some derivations and
questions related to the course content, and programming tasks. At the
exercise you have to mark the ones you have solved and be prepared to
At minimum finish 50% of the exercises.
20% of final score is based on amount of exercises completed in an acceptable level.
At the beginning of the course some project work
topics will be provided, but you can also suggest your own according to
your personal preference. You can work on this alone are in pairs.
At the end of the course, you will give a lecture and demonstration of your work at the lecture time.
Project work is 40% score
40% of the score.
Workload (valid 01.08.2018-31.07.2020):
48 h contact teaching, 85 h independent studies
Study Material (valid 01.08.2018-31.07.2020):
Prerequisites (valid 01.08.2018-31.07.2020):
Python progamming and linear algebra. Mathematica and Matlab skills will be useful
Grading Scale (valid 01.08.2018-31.07.2020):
Registration for Courses (valid 01.08.2018-31.07.2020):
Further Information (valid 01.08.2018-31.07.2020):
Language class: 3