|
|
|
||
Last update: Hrnčiřík Pavel doc. Ing. Ph.D. (17.06.2020)
|
|
||
Last update: Hrnčiřík Pavel doc. Ing. Ph.D. (17.06.2020)
Students will be able to: Create predictions and robust models based on data. Classify data. Choose a suitable model and method for solving the problem. Work with Keras and Tensorflow frameworks. Validate models and evaluate their accuracy. |
|
||
Last update: Hrnčiřík Pavel doc. Ing. Ph.D. (17.06.2020)
Z: François CHOLLET, Deep learning v jazyku Python: knihovny Keras, Tensorflow, Grada Publishing, Praha, 2019. D: Sebastian RASCHKA, Vahid MIRJALILI, Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2, Packt Publishing, Birmingham, 2019. |
|
||
Last update: Hrnčiřík Pavel doc. Ing. Ph.D. (17.06.2020)
Electronic teaching materials for the course. |
|
||
Last update: Hrnčiřík Pavel doc. Ing. Ph.D. (17.06.2020)
1 Data normalization, transformation, coding. 2 Nonlinear regression analysis. 3 Support vector machine (SVM). 4 Gradient methods. 5 Selected structures of neural networks (MLP, RBF). 6 Self-organizing maps. 7 Project. 8 Nearest Neighbors Algorithm. 9 Cluster analysis. 10 Decision trees. 11 Validation, evaluation of classification accuracy, feature extraction. 12 Convolutional neural networks. 13 Recurrent neural networks. 14 Use of Tensorflow framework in chemistry. |
|
||
Last update: Hrnčiřík Pavel doc. Ing. Ph.D. (17.06.2020)
Basic knowledge of mathematical statistics and programming in Python. |
|
||
Last update: Hrnčiřík Pavel doc. Ing. Ph.D. (17.06.2020)
Introduction to Python |
|
||
Last update: Hrnčiřík Pavel doc. Ing. Ph.D. (17.06.2020)
Splnění průběžných a zápočtových testů, obhajoba individuálního projektu, zkouškový test. |
Teaching methods | ||||
Activity | Credits | Hours | ||
Účast na přednáškách | 1 | 28 | ||
Příprava na přednášky, semináře, laboratoře, exkurzi nebo praxi | 1.1 | 30 | ||
Práce na individuálním projektu | 1.4 | 40 | ||
Příprava na zkoušku a její absolvování | 0.5 | 14 | ||
Účast na seminářích | 1 | 28 | ||
5 / 5 | 140 / 140 |