3.8 Proceedings Paper

Quasi-orthogonality and intrinsic dimensions as measures of learning and generalisation

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Physics, Multidisciplinary

Scikit-Dimension: A Python Package for Intrinsic Dimension Estimation

Jonathan Bac et al.

Summary: This technical note introduces an open-source Python package called scikit-dimension for intrinsic dimension estimation. The package provides a uniform implementation of various known ID estimators based on scikit-learn API, allowing evaluation of global and local intrinsic dimension as well as generating synthetic datasets. It is developed with tools to assess code quality, coverage, unit testing and continuous integration.

ENTROPY (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Demystification of Few-shot and One-shot Learning

Ivan Y. Tyukin et al.

Summary: This work presents mathematical foundations and conditions for successful one-shot and few-shot learning, based on intrinsic properties of high-dimensional spaces. By ensuring certain data non-concentration conditions, a sufficiently high-dimensional learning machine environment or latent decision space can easily learn a large class of objects from few examples.

2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) (2021)

Article Multidisciplinary Sciences

Benign overfitting in linear regression

Peter L. Bartlett et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2020)

Review Biology

The unreasonable effectiveness of small neural ensembles in high-dimensional brain

Alexander N. Gorban et al.

PHYSICS OF LIFE REVIEWS (2019)

Proceedings Paper Computer Science, Artificial Intelligence

On Network Design Spaces for Visual Recognition

Ilija Radosavovic et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Review Multidisciplinary Sciences

Blessing of dimensionality: mathematical foundations of the statistical physics of data

A. N. Gorban et al.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES (2018)

Article Computer Science, Artificial Intelligence

Extreme-value-theoretic estimation of local intrinsic dimensionality

Laurent Amsaleg et al.

DATA MINING AND KNOWLEDGE DISCOVERY (2018)

Article Computer Science, Information Systems

Correction of AI systems by linear discriminants: Probabilistic foundations

A. N. Gorban et al.

INFORMATION SCIENCES (2018)

Article Multidisciplinary Sciences

Estimating the intrinsic dimension of datasets by a minimal neighborhood information

Elena Facco et al.

SCIENTIFIC REPORTS (2017)

Article Computer Science, Information Systems

Approximation with random bases: Pro et Contra

Alexander N. Gorban et al.

INFORMATION SCIENCES (2016)

Article Computer Science, Artificial Intelligence

Novel high intrinsic dimensionality estimators

A. Rozza et al.

MACHINE LEARNING (2012)

Article Engineering, Electrical & Electronic

On Local Intrinsic Dimension Estimation and Its Applications

Kevin M. Carter et al.

IEEE TRANSACTIONS ON SIGNAL PROCESSING (2010)

Article Computer Science, Artificial Intelligence

Translated poisson mixture model for stratification learning

Gloria Haro et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2008)