Lecture topics by week of the semester: 1. Introduction to artificial intelligence, machine learning, basic concepts, programming languages and frameworks and modules. 2. Basic machine learning tasks - detection, classification, regression, prediction, metrics for determining quality. 3. Basic models for machine learning, supervised learning, forced learning. 4. Data decorrelation, principal component analysis. 5. Linear regression, support vector method. 6. Feedforward neural networks, TensorFlow, Keras, PyTorch. 7. Deep neural networks. 8. Fully convolutional neural networks. 9. Hardware acceleration of neural networks. 10. State space search - uninformed methods. 11. State space search - informed methods. 12. Game theory, game playing. 13. Threats and opportunities of artificial intelligence. The content of the exercises corresponds to the topics of the lectures.
|
The aim of the course is to familiarize students with the basic aspects of machine learning and artificial intelligence, to provide an overview of software tools for solving typical machine learning tasks, and to teach students how to design and create solutions to engineering problems using basic machine learning and artificial intelligence models.
After completing the course, students demonstrate knowledge, abilities, and skills that allow them to independently and creatively solve engineering problems using basic machine learning and artificial intelligence models.
|