|
Lecturer(s)
|
-
Pozdílek Martin, Ing. Ph.D.
|
|
Course content
|
1. Introduction to artificial intelligence, machine learning, basic concepts, approaches, tasks and machine learning models 2. Preparation and analysis of datasets for machine learning 3. Linear regression 4. Data decorrelation, principal component analysis (PCA), metrics for determining model quality 5. Classification, support vector machine (SVM), k-means 6. State space search - problem formulation, computer representation 7. State space search - uninformed methods, informed methods 8. Game theory, gaming 9. Forward neural networks, TensorFlow, Keras, PyTorch, hardware acceleration of neural networks 10. Deep neural networks, backpropagation algorithm 11. Fully convolutional neural networks 12. Recurrent neural networks 13. Threats and opportunities of artificial intelligence Exercise 1. Introduction to python and jupyter notebook 2. Statistical analysis of dataset 3. Linear regression 4. Principal components analysis 5. kmeans, SVM 6. State space 7. Searching the state space 8. Game theory, pishquares 9. Artificial neural network 10. Classification in ANN 11. Convolutional ANN 12. Recurrent ANN
|
|
Learning activities and teaching methods
|
Monologic (reading, lecture, briefing), Dialogic (discussion, interview, brainstorming), Demonstration, Skills training, Work-related activities
- Term paper
- 24 hours per semester
- Home preparation for classes
- 63 hours per semester
- Contact teaching
- 4 hours per semester
- Practical training
- 4 hours per semester
- Preparation for an exam
- 25 hours per semester
|
|
Learning outcomes
|
The aim of the course is to introduce students to the basic aspects of machine learning and artificial intelligence, to provide an overview of software tools for solving typical machine learning problems, and to teach students to use basic machine learning and artificial intelligence models to design and create solutions to engineering problems. Upon completion of the course, students will demonstrate the knowledge, skills and abilities to independently solve engineering problems creatively using basic machine learning and artificial intelligence models.
The course aims to familiarize students with the possibilities of practical use of mathematical models in practice. The emphasis is on understanding the main ideas of mathematical methods and the ability of students to solve practical problems independently using appropriate software.
|
|
Prerequisites
|
unspecified
|
|
Assessment methods and criteria
|
unspecified
Written, oral, evaluation of assigned practical work Credit Completion of 12 out of 18 tasks assigned in the practical Exam Create an AI project on one of the typical AI tasks and successfully defend the project
|
|
Recommended literature
|
-
BURKOV, Andriy. The Hundred-Page Machine Learning Book. 2019. ISBN 978-19-995-7950-0.
-
CHOLLET, François. Deep learning v jazyku Python: knihovny Keras, Tensorflow. Praha: Grada Publishing, 2019. ISBN 978-80-247-3100-1.
-
MAŘÍK, V., ŠTĚPÁNKOVÁ, O., LAŽANSKÝ, j. Umělá inteligence 1. Praha: Academia, 2004. ISBN 80-200-0496-3.
-
MAŘÍK, Vladimír, Olga ŠTĚPÁNKOVÁ a Jiří LAŽANSKÝ. Umělá inteligence 3. Praha: Academia, 2001. ISBN 80-200-0472-6.
-
MAŘÍK, Vladimír, Olga ŠTĚPÁNKOVÁ a Jiří LAŽANSKÝ. Umělá inteligence 4. Praha: Academia, 2003. ISBN 80-200-1044-0.
-
MAŘÍK, Vladimír, Olga ŠTĚPÁNKOVÁ a Jiří LAŽANSKÝ. Umělá inteligence 5. Praha. 2007.
|