activity
20182026
most citedHigh-dimensional separability for one- and few-shot learning

12 citations · 12 across the 3 of their papers we have counts for

collaborators
Showing 2020Show all

2 papers · 1 filter

cs.AI2020

General stochastic separation theorems with optimal bounds

Bogdan Grechuk, Alexander N. Gorban, Ivan Y. Tyukin

Phenomenon of stochastic separability was revealed and used in machine learning to correct errors of Artificial Intelligence (AI) systems and analyze AI instabilities. In high-dime…

math.MG2020

A convex cover for closed unit curves has area at least 0.1

Bogdan Grechuk, Sittichoke Som-am

We improve a lower bound for the smallest area of convex covers for closed unit curves from 0.0975 to 0.1, which makes it substantially closer to the current best upper bound 0.110…