Fast construction of correcting ensembles for legacy Artificial Intelligence systems: Algorithms and a case study

This paper presents a new approach for constructing simple and computationally efficient improvements of generic Artificial Intelligence (AI) systems, including Multilayer and Deep Learning neural networks. The improvements are small network ensembles added to the existing AI architectures. Theoreti...

Full description

Saved in:
Bibliographic Details
Published inInformation sciences Vol. 485; pp. 230 - 247
Main Authors Tyukin, Ivan Yu, Gorban, Alexander N., Green, Stephen, Prokhorov, Danil
Format Journal Article
LanguageEnglish
Published Elsevier Inc 01.06.2019
Subjects
Artificial intelligence
Measure concentration
Neural ensembles
Perceptron
Stochastic separation theorems
Measure concentration
Perceptron
68T42
68T05
Stochastic separation theorems
Artificial intelligence
97R40
Neural ensembles
60F05
Online AccessGet full text

Cover

More Information
Summary:This paper presents a new approach for constructing simple and computationally efficient improvements of generic Artificial Intelligence (AI) systems, including Multilayer and Deep Learning neural networks. The improvements are small network ensembles added to the existing AI architectures. Theoretical foundations of the approach 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 approach enables fast removal of the AI’s errors with probability close to one on the datasets which may be exponentially large in dimension. The approach is illustrated with numerical examples and a case study of digits recognition in American Sign Language.
ISSN:0020-0255
1872-6291
DOI:10.1016/j.ins.2018.11.057