NNDrone: a toolkit for the mass application of machine learning in High Energy Physics

TL;DR

NNDrone is a versatile toolkit that standardizes and parallelizes machine learning classifiers for high energy physics, enabling label-free training of drone neural networks to efficiently identify interesting events.

Contribution

The paper introduces NNDrone, a novel toolkit that converts various classifiers into a unified form and trains drone neural networks without labeled data.

Findings

Successfully standardizes different classifiers into a single framework

Demonstrates label-free training of drone neural networks

Enhances event selection efficiency in high energy physics

Abstract

Machine learning has proven to be an indispensable tool in the selection of interesting events in high energy physics. Such technologies will become increasingly important as detector upgrades are introduced and data rates increase by orders of magnitude. We propose a toolkit to enable the creation of a drone classifier from any machine learning classifier, such that different classifiers may be standardised into a single form and executed in parallel. We demonstrate the capability of the drone neural network to learn the required properties of the input neural network without the use of any labels from the training data, only using appropriate questioning of the input neural network.