The course is focused on comprehension of commonly used neural network architectures, suitable for various types of solved problems and processed data. Lectures cover the necessary theory, but are mainly focused on practical aspects of neural network design. For seminars, students will try to train the designed models of neural networks and further optimize them.

Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, 2016. http://www.deeplearningbook.org

Feed-forward neural networks

• basic architectures and activation functions

• optimization algorithms for training

• selection of hyperparameters

Regularization of neural network models

• commonly used regularization techniques - dropout, label-smoothing

Convolutional neural networks

• convolution layers, normalization

• architectures suitable for deep convolutional neural networks

• pre-training and fine-tuning of deep neural networks

Recurrent neural networks

• basic recurrent networks and problems of their training

• LSTM, GRU

• bidirectional and deep recurrent networks

Transformer architecture

Design and optimization of neural networks in various environments - Python, MATLAB