Data Analysis and Computational Intelligence
Code | Completion | Credits | Range |
---|---|---|---|
W31OZ001 | ZK | 39P+39C |
- Course guarantor:
- Lecturer:
- Tutor:
- Supervisor:
- Department of Mechanics, Biomechanics and Mechatronics
- Synopsis:
-
Doctoral students gain an overview of computational intelligence and data analysis methods and can orientate
themselves in the classical and latest trends in artificial intelligence using machine learning and neural networks. Deeper insights and skills will be gained by preparing the subject project for a given topic according to the particular doctoral candidate or study group.
History of computational and artificial intelligence, data analytics and datamining
Principles of machine learning, adaptation algorithms, optimization
Principle of supervised neural networks for prediction and classification
Basic methods of data analysis (linear and nonlinear correlation analysis, MI, PCA, SVD)
Methods of clustering and N-dimensional data visualization methods (k-means, PCA, SVD, tSNE)
Self-organizing maps
Fundamentals of large data processing methods and tools (BigData, k-medoids, Hadoop, MapReduce, Spark)
Autoencoders for classification and reduction of dimensionality
Detection of unexpected states by neural networks
New methods of computational intelligence for data processing (DeepLearning, Transfer Learning, Transformer Neural Networks, ...)
- Requirements:
- Syllabus of lectures:
- Syllabus of tutorials:
- Study Objective:
- Study materials:
-
DAVID B FOGEL, DERONG LIU a JAMES M KELLER. Fundamentals of Computational Intelligence: Neural Networks, Fuzzy Systems, and Evolutionary Computation. Piscataway, NJ: IEEE Press, 2016. ISBN 978-1-119-21434-2.
RAMSUNDAR, Bharath a Reza Bosagh ZADEH. TensorFlow for deep learning: from linear regression to
reinforcement learning. 2018. ISBN 978-1-4919-8042-2.
LECUN, Yann, Yoshua BENGIO a Geoffrey HINTON. Deep learning. Nature. 2015, 521(7553), 436444.
BUKOVSKY, Ivo, Witold KINSNER a Noriyasu HOMMA. Learning Entropy as a Learning-Based Information Concept. Entropy. 2019, 21(2), 166. ISSN 1099-4300. Dostupné z: doi:10.3390/e21020166
- Note:
- Further information:
- No time-table has been prepared for this course
- The course is a part of the following study plans: