Machine Learning for New Physics Searches

TL;DR

This paper introduces a neural network-based, model-independent approach for detecting new physics phenomena in datasets dominated by background noise, aiming to improve discovery potential in high-energy physics experiments.

Contribution

It presents a novel neural network technique specifically designed for model-independent searches in background-rich datasets, advancing current methods in new physics detection.

Findings

Demonstrates effectiveness of neural networks in background-dominated scenarios

Provides a new technique for model-independent physics searches

Enhances sensitivity to potential new physics signals

Abstract

This is the summary of a talk given at CIPANP 2018. I briefly introduce neural networks and then discuss a new technique for model-independent new physics searches in background-dominated datasets.