English

Not applicable.

The graduate is able to: (a) understand quantum computer problems, specifically, it is able to recognize when such a calculation is advantageous; (b) calculate and design basic algorithms for quantum computers.

Not applicable.

Not applicable.

Not applicable.

Not applicable.

1 - Organization of teaching, introduction to machine learning, motivation
2 - Basics of linear algebra for ML
3 - Support vectors, Support vector Machines
4 - Introduction to artificial neural networks, representation,
classification
5 - Neural network training (linear regression, Gradient method,
polynomial regression, ...)
6 - Convolutional neural networks
7 - Recursive neural networks
8 - Hyperparameter tuning, batch normalization and programming frameworks
9 - Learning without supervision
10 - Generative learning, autoencoders, GAN
11 - Machine learning on a large scale

Not applicable.

The aim of the course is to acquaint students with basic concepts of quantum physics and algorithms necessary for working with quantum information. Quantum mechanics as a subject of physics examines how microscopic physical dynamic systems change in nature. However, in quantum information theory, quantum systems are studied as theoretical systems and concepts abstracted from quantum mechanics itself. The aim of computer exercises is to gain practical experience with the implementation of algorithms using quantum theory.

Not applicable.

Not applicable.

Not applicable.

ERTEL, W., Introduction to Artificial Intelligence, 2018, Springer (EN)
GOODFELLOW, I. et al., Deep learning, 2016, MIT Press (EN)
CHOLLET, F. Deep Learning with Python, 2017, Manning Publications (EN)

Not applicable.