🚀 @SBERLOGABIG вебинар по дата сайнс:
👨‍🔬 Дмитрий Кобак «Contrastive and neighbor embedding methods for data visualization» ( Контрастные методы и методы
ближайших соседей для визуализации данных )
⌚️ Четверг 25 мая, 18.00 по Москве

Add to Google Calendar

In recent years, neighbor embedding methods like t-SNE and UMAP have become widely used across several application fields, in particular in single-cell biology. They are also widely used for visualizing large collections of documents and/or images used to train modern deep learning architectures such as large language models or diffusion models. Given this academic and public attention, it is very important to understand possibilities, shortcomings, and trade-offs of neighbor embedding methods. I am going to present our recent work on
the attraction-repulsion spectrum of neighbor embeddings and the involved trade-offs. I am also going to explain how neighbor embeddings are related to contrastive learning, a popular framework for self-supervised learning of image data. This will lead to our recent work on contrastive visualizations of image datasets. In the second part of the talk, I will present our ongoing work on visualization of scientific literature, in particular biomedical research papers from the PubMed library.

О докладчике: Дмитрий Кобак - дата сайнтист в Tübingen University, один из ведущих специалистов в мире по методам снижения размерности в анализе данных.

Ссылка на зум будет в https://t.me/sberlogabig перед докладом.
Видео записи: https://www.youtube.com/c/SciBerloga