One-Trial Correction of Legacy AI Systems and Stochastic Separation Theorems

TL;DR

This paper introduces a method for quickly tuning existing AI systems by adding a cascade of perceptrons, leveraging high-dimensional measure concentration to improve performance without retraining.

Contribution

It presents a novel one-trial correction technique for legacy AI systems using perceptron cascades based on high-dimensional measure concentration principles.

Findings

Effective on-the-fly tuning of AI systems demonstrated

Improvement achieved without retraining or extensive data

Applicable to various AI models, including deep networks

Abstract

We consider the problem of efficient "on the fly" tuning of existing, or {\it legacy}, Artificial Intelligence (AI) systems. The legacy AI systems are allowed to be of arbitrary class, albeit the data they are using for computing interim or final decision responses should posses an underlying structure of a high-dimensional topological real vector space. The tuning method that we propose enables dealing with errors without the need to re-train the system. Instead of re-training a simple cascade of perceptron nodes is added to the legacy system. The added cascade modulates the AI legacy system's decisions. If applied repeatedly, the process results in a network of modulating rules "dressing up" and improving performance of existing AI systems. Mathematical rationale behind the method is based on the fundamental property of measure concentration in high dimensional spaces. The method is illustrated with an example of fine-tuning a deep convolutional network that has been pre-trained to detect pedestrians in images.