Journal
INFORMATION SCIENCES
Volume 564, Issue -, Pages 124-143Publisher
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2021.01.022
Keywords
Stochastic separation theorems; Artificial intelligence; Machine learning; Computer vision
Categories
Funding
- Innovate UK Knowledge Transfer Partnership [KTP010522]
- UKRI Turing AI Acceleration Fellowship [EP/V025295/1]
- 111 Project [B16009]
- Russian Science Foundation [191900566]
- Ministry of Science and Higher Education of Russian Federation [14.Y26.31.0022]
- EPSRC [EP/V025295/1] Funding Source: UKRI
Ask authors/readers for more resources
This paper introduces a theory and algorithms that enable Artificial Intelligence systems to continuously improve with quantifiable guarantees by reducing classification errors. It is capable of building few-shot AI correction algorithms with linear training complexity and lower computational complexity, making it suitable for resource-constrained environments.
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 more specifically remove classification errors-over time. This is distinct from state-of-the-art machine learning, AI, and software approaches. The theory enables building few-shot AI correction algorithms and provides conditions justifying their successful application. Another feature of this approach is that, in the supervised setting, the computational complexity of training is linear in the number of training samples. At the time of classification, the computational complexity is bounded by few inner product calculations. Moreover, the implementation is shown to be very scalable. This makes it viable for deployment in applications where computational power and memory are limited, such as embedded environments. It enables the possibility for fast on-line optimisation using improved training samples. The approach is based on the concentration of measure effects and stochastic separation theorems and is illustrated with an example on the identification faulty processes in Computer Numerical Control (CNC) milling and with a case study on adaptive removal of false positives in an industrial video surveillance and analytics system. (c) 2021 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available