Subjects

• sparse kernel machines (SVM, RVM) • graphical models • mixture models and expectation maximization • principal component analysis (PCA) • Markov models and linear dynamical systems • Hopfield map • recurrent neural network

Last update: Krtička Milan, prof. Mgr., Ph.D. (13.02.2023)

• use of neural networks for fast simulation, generative models • use of neural networks for tracking – application of Kalman filter • modelling of triggering using neural networks • neural networks for particle identification, event classification, event shapes, fast calorimeter simulation • application of neural networks in accelerator physics – detection of anomalies in beam position monitoring, suggestion of correction tools for optimization of linear optics, optimization of the collimation system, lifetime and performance optimization and detection of hidden correlations

Last update: Krtička Milan, prof. Mgr., Ph.D. (13.02.2023)

books

[1] Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer-Verlag Berlin, Heidelberg, ISBN:0-387-31073-8

[2] Kevin Gurney, An introduction to neural networks, UCL Press, ISBN: 1-85728-673-1

[3] Richard O. Duda, Peter E. Hart, David G. Stork, Pattern Classification (2nd Edition), Wiley-Interscience New York, NY, USA, ISBN:0471056693

[4] Tom M. Mitchell, Machine Learning, McGraw-Hill, ISBN: 070428077

[5] S. Theodoridis K. Koutroumbas, Pattern Recognition, Elsevier, ISBN:9781597492720

[6] Stuart J. Russell and Peter Norvig, Artificial Intelligence A Modern Approach, Prentice Hall Press Upper Saddle, River, NJ, USA, ISBN:0136042597 9780136042594

online books:

[1] Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, www.deeplearningbook.org

[2] Michael Nielsen, Neural Networks and Deep Learning, http://neuralnetworksanddeeplearning.com/index.html