• Corpus ID: 246863693

Interpreting a Machine Learning Model for Detecting Gravitational Waves

@article{Safarzadeh2022InterpretingAM,
  title={Interpreting a Machine Learning Model for Detecting Gravitational Waves},
  author={Mohammadtaher Safarzadeh and Asad Khan and Eliu A. Huerta and Martin Wattenberg},
  journal={ArXiv},
  year={2022},
  volume={abs/2202.07399}
}
We describe a case study of translational research, applying interpretability techniques developed for computer vision to machine learning models used to search for and find gravitational waves. The models we study are trained to detect black hole merger events in non-Gaussian and non-stationary advanced Laser Interferometer Gravitational-wave Observatory (LIGO) data. We produced visualizations of the response of machine learning models when they process advanced LIGO data that contains real… 
View PDF on arXiv
View With Semantic Reader

References

SHOWING 1-10 OF 52 REFERENCES
Deep learning ensemble for real-time gravitational wave detection of spinning binary black hole mergers
Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation with LIGO Data
TLDR
Comparisons show that Deep Filtering is far more computationally efficient than matched-filtering, while retaining similar sensitivity and lower errors, allowing real-time processing of weak time-series signals in non-stationary non-Gaussian noise, with minimal resources.
Unsupervised learning and data clustering for the construction of Galaxy Catalogs in the Dark Energy Survey
Accelerated, scalable and reproducible AI-driven gravitational wave detection
TLDR
A workflow that connects the Data and Learning Hub for Science, a repository for publishing AI models, with the Hardware Accelerated Learning (HAL) cluster, using funcX as a universal distributed computing service to open new pathways to conduct reproducible, accelerated, data-driven discovery.
Deep Learning at Scale for the Construction of Galaxy Catalogs in the Dark Energy Survey.
TLDR
It is demonstrated that knowledge from deep learning algorithms can be transferred to classify galaxies that overlap both SDSS and DES surveys, achieving state-of-the-art accuracy and shown that these newly labeled datasets can be combined with unsupervised recursive training to create large-scale DES galaxy catalogs in preparation for the Large Synoptic Survey Telescope era.
Rapid detection of gravitational waves from compact binary mergers with PyCBC Live
We introduce an efficient and straightforward technique for rapidly detecting gravitational waves from compact binary mergers. We show that this method achieves the low latencies required to alert…
Deep transfer learning for star cluster classification: I. application to the PHANGS–HST survey
TLDR
Given the relatively small and unbalanced nature of existing, human-labelled star cluster datasets, the knowledge of neural network models for real-object recognition is transferred to classify star clusters candidates into four morphological classes to automate classification for these objects at scale, and the creation of a standardized dataset.
Deep Learning and Its Application to LHC Physics
TLDR
The connections between machine learning and high-energy physics data analysis are explored, followed by an introduction to the core concepts of neural networks, examples of the key results demonstrating the power of deep learning for analysis of LHC data, and discussion of future prospects and concerns.
A Novel Activation Maximization-based Approach for Insight into Electrophysiology Classifiers
TLDR
The approach is the first adaptation of activation maximization to the domain of raw electrophysiology classification and has implications for explaining any classifier trained on highly dynamic, long time-series.
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning
TLDR
This introductory paper presents recent developments and applications in the deep learning field and makes a plea for a wider use of explainable learning algorithms in many applications.
...
...