[1] EKMAN, Magnus. Learning deep learning: theory and practice of neural networks, computer vision, natural language processing, and transformers using TensorFlow. Boston: Addison-Wesley, [2022]. ISBN 0137470355 .
[2] SZELISKI, Richard. Computer vision: algorithms and applications. Second edition. Texts in computer science. Cham, Switzerland: Springer, [2022]. ISBN 978-3-030-34372-9 .
Artificial Intelligence for Industrial Applications
| Language of instruction | angličtina, čeština |
|---|---|
| Code | 450-2109 |
| Abbreviation | UIPA |
| Course title | Artificial Intelligence for Industrial Applications |
| Coordinating department | Department of Cybernetics and Biomedical Engineering |
| Course coordinator | Ing. Dominik Vilímek, Ph.D. |
Summary
The course serves as a practical guide for implementing AI in engineering practice. The goal is to master a 'Data-Centric' approach – from collecting and cleaning multimodal data (1D signals, 2D images, 3D) to model deployment. Students will learn to train modern architectures (YOLO, U-Net, Transformer), integrate local LLMs, and optimize solutions for edge devices (NVIDIA Jetson) using containerization. Emphasis is placed on pipeline robustness and transferability to production.
Literature
Advised literature
[1] EKMAN, Magnus. Learning deep learning: theory and practice of neural networks, computer vision, natural language processing, and transformers using TensorFlow. Boston: Addison-Wesley, [2022]. ISBN 0137470355 .
[2] SZELISKI, Richard. Computer vision: algorithms and applications. Second edition. Texts in computer science. Cham, Switzerland: Springer, [2022]. ISBN 978-3-030-34372-9 .
[2] SZELISKI, Richard. Computer vision: algorithms and applications. Second edition. Texts in computer science. Cham, Switzerland: Springer, [2022]. ISBN 978-3-030-34372-9 .