[28. February] Let's Talk ML

Petr Nevyhoštěný - Introduction to Graph Neural Networks (slides)

Deep learning has achieved a great success in machine learning tasks, ranging from image and video classification, speech recognition and natural language understanding. However, there is an increasing number of applications where data are from non-Euclidean domains and are represented as graph structures. This talk will be a brief introduction to the topic of graph neural networks which attempt to deal with these problems.

Radek Bartyzal - Dropout is a special case of the stochastic delta rule: faster and more accurate deep learning (slides)

This talk will explain how is replacing weights with random variables connected to Dropout and what benefits it may bring.


Follow Us

Copyright (c) Data Science Laboratory @ FIT CTU 2014–2016. All rights reserved.