Fast Construction of Correcting Ensembles for Legacy Artificial Intelligence Systems: Algorithms and a Case Study

This paper presents a technology for simple and computationally efficient improvements of a generic Artificial Intelligence (AI) system, including Multilayer and Deep Learning neural networks. The improvements are, in essence, small network ensembles constructed on top of the existing AI architectur...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Tyukin, Ivan Y, Gorban, Alexander N, Green, Stephen, Prokhorov, Danil
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 13.02.2019
Subjects
Algorithms
Artificial intelligence
Case studies
Computational efficiency
Computer Science - Artificial Intelligence
Computer Science - Learning
Digits
Machine learning
Multilayers
Neural networks
Statistical analysis
Systematic errors
Online AccessGet full text

Cover

More Information
Summary:This paper presents a technology for simple and computationally efficient improvements of a generic Artificial Intelligence (AI) system, including Multilayer and Deep Learning neural networks. The improvements are, in essence, small network ensembles constructed on top of the existing AI architectures. Theoretical foundations of the technology are based on Stochastic Separation Theorems and the ideas of the concentration of measure. We show that, subject to mild technical assumptions on statistical properties of internal signals in the original AI system, the technology enables instantaneous and computationally efficient removal of spurious and systematic errors with probability close to one on the datasets which are exponentially large in dimension. The method is illustrated with numerical examples and a case study of ten digits recognition from American Sign Language.
Bibliography:SourceType-Working Papers-1
ObjectType-Working Paper/Pre-Print-1
content type line 50
ISSN:2331-8422
DOI:10.48550/arxiv.1810.05593