Blessing of dimensionality at the edge

TL;DR

This paper introduces a scalable AI approach leveraging measure concentration and stochastic separation theorems, enabling incremental learning with guaranteed error reduction suitable for resource-limited environments.

Contribution

It presents a novel theory and algorithms for continuous, incremental AI learning with provable guarantees, distinct from traditional machine learning methods.

Findings

Linear training complexity in the number of samples

Low computational cost at classification due to few inner products

Scalable implementation suitable for embedded systems

Abstract

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. 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.