Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks

07/23/2022
by   Jingkai Yan, et al.
7

Gravitational wave astronomy is a vibrant field that leverages both classic and modern data processing techniques for the understanding of the universe. Various approaches have been proposed for improving the efficiency of the detection scheme, with hierarchical matched filtering being an important strategy. Meanwhile, deep learning methods have recently demonstrated both consistency with matched filtering methods and remarkable statistical performance. In this work, we propose Hierarchical Detection Network (HDN), a novel approach to efficient detection that combines ideas from hierarchical matching and deep learning. The network is trained using a novel loss function, which encodes simultaneously the goals of statistical accuracy and efficiency. We discuss the source of complexity reduction of the proposed model, and describe a general recipe for initialization with each layer specializing in different regions. We demonstrate the performance of HDN with experiments using open LIGO data and synthetic injections, and observe with two-layer models a 79% efficiency gain compared with matched filtering at an equal error rate of 0.2%. Furthermore, we show how training a three-layer HDN initialized using two-layer model can further boost both accuracy and efficiency, highlighting the power of multiple simple layers in efficient detection.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/08/2021

Generalized Approach to Matched Filtering using Neural Networks

Gravitational wave science is a pioneering field with rapidly evolving d...
research
11/09/2020

Improved deep learning techniques in gravitational-wave data analysis

In recent years, convolutional neural network (CNN) and other deep learn...
research
08/23/2021

Understanding the Basis of Graph Convolutional Neural Networks via an Intuitive Matched Filtering Approach

Graph Convolutional Neural Networks (GCNN) are becoming a preferred mode...
research
04/08/2022

Quantum encoding is suitable for matched filtering

Matched filtering is a powerful signal searching technique used in sever...
research
10/31/2018

The Medico-Task 2018: Disease Detection in the Gastrointestinal Tract using Global Features and Deep Learning

In this paper, we present our approach for the 2018 Medico Task classify...
research
12/08/2018

Signal recognition and background suppression by matched filters and neural networks for Tunka-Rex

The Tunka Radio Extension (Tunka-Rex) is a digital antenna array, which ...
research
12/11/2018

Deep networks with probabilistic gates

We investigate learning to probabilistically bypass computations in a ne...

Please sign up or login with your details

Forgot password? Click here to reset