High-dimensional brain in a high-dimensional world: Blessing of dimensionality

AN Gorban, VA Makarov, IY Tyukin - Entropy, 2020 - mdpi.com
High-dimensional data and high-dimensional representations of reality are inherent features
of modern Artificial Intelligence systems and applications of machine learning. The well …

How deep should be the depth of convolutional neural networks: a backyard dog case study

AN Gorban, EM Mirkes, IY Tyukin - Cognitive Computation, 2020 - Springer
The work concerns the problem of reducing a pre-trained deep neuronal network to a
smaller network, with just few layers, whilst retaining the network's functionality on a given …

[HTML][HTML] Blessing of dimensionality at the edge and geometry of few-shot learning

IY Tyukin, AN Gorban, AA McEwan… - Information …, 2021 - Elsevier
In this paper we present theory and algorithms enabling classes of Artificial Intelligence (AI)
systems to continuously and incrementally improve with a priori quantifiable guarantees–or …

MyI-Net: Fully automatic detection and quantification of myocardial infarction from cardiovascular MRI images

S Wang, AM Abdelaty, K Parke, JR Arnold, GP McCann… - Entropy, 2023 - mdpi.com
Myocardial infarction (MI) occurs when an artery supplying blood to the heart is abruptly
occluded. The “gold standard” method for imaging MI is cardiovascular magnetic resonance …

Myocardial infarction detection and quantification based on a convolution neural network with online error correction capabilities

SH Wang, G McCann, I Tyukin - 2020 International Joint …, 2020 - ieeexplore.ieee.org
Myocardial infarction (MI), more commonly known as heart attack, occurs when the blood
flow to the heart decreases or stops. Over 100,000 people each year in the UK suffer from an …

AI automation and application in diverse sectors

SM Mohammad - International Journal of Computer Trends and …, 2020 - papers.ssrn.com
Artificial intelligence, commonly referred to as AI, has, in recent years, transformed the
nature of human life in almost every aspect that is connected to human life. The aspects …

Machine learning approach to the Floquet–Lindbladian problem

V Volokitin, I Meyerov, S Denisov - Chaos: An Interdisciplinary Journal …, 2022 - pubs.aip.org
Similar to its classical version, quantum Markovian evolution can be either time-discrete or
time-continuous. Discrete quantum Markovian evolution is usually modeled with completely …

Kernel stochastic separation theorems and separability characterizations of kernel classifiers

IY Tyukin, AN Gorban, B Grechuk… - 2019 International Joint …, 2019 - ieeexplore.ieee.org
In this work we provide generalizations and extensions of stochastic separation theorems to
kernel classifiers. A general separability result for two random sets is also established. We …

Ошибки интеллекта, основанного на данных

АН Горбань - Интеллектуальные системы в науке и технике …, 2020 - elibrary.ru
Настоящий доклад представляет собой краткий отчет о проекте, использующем новый
подход к повышению интеллектуальной эффективности искусственного интеллекта …

Learning and Generalisation for High-dimensional Data

MH Alkhudaydi - 2021 - figshare.le.ac.uk
Modern data-driven Artificial Intelligence models are based on large datasets which have
been recently made available to practitioners. Significant efforts have been put into …