Master of Applied Mathematics and Information Technology (FAMCS at Belarusian State University). Currently he studies master’s program at the Faculty of computer systems and networks BSUIR. Spheres of professional and academic interests: Deep Learning, Image Processing, Natural Language Processing.
Topic: Generative modeling with Convolutional Neural Networks
Short Description: During this speech we will talk about main ideas behind generative modeling with CNNs (from basics to GAN framework). We’ll try to find answers to the following questions:
– How to train a neural network to fool a discriminative deep learning model?
– How to train a neural network to produce photorealistic images?
– What difficulties can we face and how to avoid them?
– How GAN framework could be used to solve real problems?