CA17137 G2Net WG1 meeting

11 Apr 2022, 12:00 → 13 Apr 2022, 18:00 Europe/Madrid

Faculty of Mathematics of the University of Valencia

Work Group 1 (WG1) aims at investigating Machine Learning (ML) techniques in gravitational wave (GW) astronomy applications: classify GW signals, recognise noise and disturbances from the instrument, as well as identify GW signals from known mechanisms and GW signals from yet unknown mechanisms.

More specifically, the goal is to design problem-specific ML pipelines by considering ready-to-use algorithms for solving classical ML tasks (clustering, classification and regression), specific data structures for the development of novel ML algorithms, as well as specific frameworks for the development of GPU-based ML solutions.

Link for remote connection to the meeting: 

https://eu.bbcollab.com/guest/b337209725e24616a07c741c95b7de5d

 

WG1 members group photo (12 Apr 2022)

 

Monday 11 April

12:00 → 12:20 Opening and Welcome: WG1 status

Convener: Michal Bejger (INFN Ferrara & CAMK PAN)

WG1 Valencia meeting April 2022.pdf

12:20 → 12:40 Simulating transient noise burst in LIGO with Generative Adversarial Networks

Speaker: Melissa Lopez

Glitch generator-wg1_g2net.pdf

12:40 → 13:00 1D CNN Denoising AutoEncoder for BBH waveforms

Speaker: Michal Bejger (INFN Ferrara & CAMK PAN)

paper_dcvae.pdf

13:00 → 14:30 Lunch

14:30 → 14:50 Complex systems in the G2net research

Speaker: Velimir Ilic

Complex systems in CA17137.pdf

14:50 → 15:20 Validation of Speech Processing Techniques for Real-Time Detection of Gravitational Waves

Speaker: Daniele Dell'Aquila

20220411_meeting_g2net.pdf

15:20 → 15:50 Detection of GW Signals Using Quadratic Time-Frequency Distributions and Deep CNNs

Speaker: Nicola Lopac

Lopac_Nikola_Presentation_g2net_Valencia_2022.pdf

15:50 → 16:15 Coffee break

16:15 → 18:05 G2Net paper discussion

Tuesday 12 April

09:30 → 10:00 Searches for Mass-Asymmetric Compact Binary Coalescence Events using Convolutional Neural Networks

Speaker: ‪Marc Andrés-Carcasona‬

AsymmetricCBC_g2net2022.pdf

10:00 → 10:30 Searching for the phase transition in the dense matter equation of state using anomaly detection technique

Speaker: Filip Morawski

wg1_meeting.pdf

10:30 → 11:00 Application of Gaussian Mixture Modelling to the Short All-sky Burst Gravitational Wave Search

Speaker: Leigh Smith

GMM-Valencia22.pdf

11:00 → 11:30 Coffee break

11:30 → 12:00 Searching for long-duration transient gravitational waves from glitching pulsars using Convolutional Neural Networks

Speaker: Luana Modafferi

LMM_g2netApril2022.pdf

12:00 → 12:30 Submission to the MLGWSC-1

Speaker: Ondřej Zelenka

zelenka_slides.pdf

12:30 → 13:00 CNN for early alert: Going down in frequency

Speaker: Grégory Baltus

Gregory_Baltus.pdf

13:00 → 14:30 Lunch

14:30 → 14:50 Vitamin: Rapid Bayesian parameter estimation of CBC signals using conditional variational autoencoders

Speaker: Bayley Joe

Vitamin_G2net.pdf

14:50 → 15:10 Core-collapse supernova detection and classification in real noise with CNN and LSTM

Speaker: Alberto Iess

WG1_meeting_Valencia_12042022_pdf.pdf

15:10 → 15:50 Open challenges in the application of DL to distributed mobile sensing

Speaker: Fabio Bonsignorio

HCV3.8VeryVeryVeryShortPDF.pdf

15:50 → 16:20 Discussion

17:00 → 19:00 Social event

Wednesday 13 April

09:30 → 10:00 Neural networks for gravitational wave trigger selection in single detector periods

Speaker: Agata Trovato

VIR-0397A-22_NeuralNetworksForGravitational.pdf

10:00 → 10:30 Modelling compact binary waveforms using machine learning methods

Speaker: Maite Mateu-Lucena

G2Net_MaiteMateuLucena.pdf

10:30 → 11:00 What could ML do for finding gravitationally lensed GWs?

Speaker: David Keitel

20220412_g2net_lensingML_v2.pdf

11:00 → 11:30 Coffee break

11:30 → 11:50 Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling

Speaker: Stella Fragkouli

StellaFragkouli_G2Net.pdf

11:50 → 12:10 Intra-domain and cross-domain transfer learning for time series data—How transferable are the features?

Speaker: Ivan Štajduhar

Intra-domain and cross-domain transfer learning for time series data.pdf

12:10 → 13:00 Discussion

13:00 → 14:30 Lunch

16:00 → 18:00 Social event