|
Lecturer(s)
|
-
Fesl Jan, Ing. Ph.D.
-
Mukherjee Amrit, Dr. Ph.D.
-
Vohnout Rudolf, Ing. Ph.D.
-
Budík Ondřej, Ing.
|
|
Course content
|
Content of tutorials/seminar: 1. Implementing contemporary research papers from the fields of artificial intelligence, machine learning, computer vision, natural language processing and others. 2. Using modern high-end hardware, such as GPUs clusters and cloud services, self-driving cars or humanoid robots. 3. Utilizing an agile process framework such as Scrum. 4. Understanding and using modern industrial software development tools such as work package trackers, code revision systems, debuggers, profilers and others. 5. Presenting R&D outcomes to stakeholders at different levels, such as fellow students, faculty members and practitioners and executives. This subject involves strong cooperation with supervisors from practice that will together with subject guarantor will influence the lab work and its content. The focus of the work in the lab should be ideally connected with the topic of master thesis.
|
|
Learning activities and teaching methods
|
Practical training
- Class attendance
- 30 hours per semester
- Semestral paper
- 120 hours per semester
|
|
Learning outcomes
|
The purpose of this course is to provide students with hands-on and AI-oriented application development experience. The students will have the opportunity to read some cutting-edge research papers and then turn them in concrete software/hardware outcomes. The development of applications will be practically realised in the newly established laboratory equipped with modern technologies like self-driving cars, humanoid robots, advanced embedded systems, GPU cluster etc.
Practical knowledge of working with advanced embedded devices.
|
|
Prerequisites
|
As these projects are completed in teams, students will also have the opportunity to elaborate on their social and language skills. At the end of the term, students will present their projects at an in-house R&D fair which will be open to the public.
|
|
Assessment methods and criteria
|
Analysis of student's work activities (technical works), Analysis of the qualification work
The presentation of the final project and its defense.
|
|
Recommended literature
|
-
A. GÉRON. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition, O'Reilly Media, Inc. 2019, ISBN: 9781492032649.
-
A. R. JHA, G. PILLAI. Mastering PyTorch, Packt Publishing 2021, ISBN: 978-1789614381.
-
C. BISHOP. Pattern Recognition and Machine Learning, Springer, 2006, ISBN: 978-0-387-31073-2.
-
E. EL KHALED. Accelerating AI with Synthetic Data, O'Reilly Media, Inc., 2020, ISBN: 9781492045984.
-
I. GOODFELLOW, Y. BENGIO AND A. COURVILLE. Deep Learning, MIT Press, 2016, ISBN: 9780262035613.
-
J. HOWARD, S. GUGGER. Deep Learning for Coders with Fastai and PyTorch: AI Applications Without a PhD, O'Reilly Media; 1st edition, 2020, ISBN: 978-1492045526.
|