We will talk about a semi-supervised learning problem known as Positive-Unlabeled learning. First, we will discuss what PU learning is and where it is applied. Then, I will present a method that I have developed for solving the problem. Prerequisites are basic knowledge of probability theory and supervised learning. Spoilers here: https://arxiv.org/pdf/1902.06965.pdf
Speaker: Dmitry Ivanov.
Presentation language: Russian.
Date and time: March 21st, 20:00-21:30.
Location: Times, room 405.
Videos from seminars will be available at http://bit.ly/MLJBSeminars
- About seminars
23 May 2019Aggregation of pairwise comparisons with reduction of biases
16 May 2019Recommendation system for writing texts in a specific domain area
25 April 2019Topic modeling of a news stream
18 April 2019Search engine based on word embeddings
11 April 2019Building execution graphs in distributed systems