Improved deep learning techniques in gravitational-wave data analysis. (arXiv:2011.04418v2 [astro-ph.HE] UPDATED)

Improved deep learning techniques in gravitational-wave data analysis. (arXiv:2011.04418v2 [astro-ph.HE] UPDATED)
<a href="http://arxiv.org/find/astro-ph/1/au:+Xia_H/0/1/0/all/0/1">Heming Xia</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Shao_L/0/1/0/all/0/1">Lijing Shao</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Zhao_J/0/1/0/all/0/1">Junjie Zhao</a>, <a href="http://arxiv.org/find/astro-ph/1/au:+Cao_Z/0/1/0/all/0/1">Zhoujian Cao</a>

In recent years, convolutional neural network (CNN) and other deep learning
models have been gradually introduced into the area of gravitational-wave (GW)
data processing. Compared with the traditional matched-filtering techniques,
CNN has significant advantages in efficiency in GW signal detection tasks. In
addition, matched-filtering techniques are based on the template bank of the
existing theoretical waveform, which makes it difficult to find GW signals
beyond theoretical expectation. In this paper, based on the task of GW
detection of binary black holes, we introduce the optimization techniques of
deep learning, such as batch normalization and dropout, to CNN models. Detailed
studies of model performance are carried out. Through this study, we recommend
to use batch normalization and dropout techniques in CNN models in GW signal
detection tasks. Furthermore, we investigate the generalization ability of CNN
models on different parameter ranges of GW signals. We point out that CNN
models are robust to the variation of the parameter range of the GW waveform.
This is a major advantage of deep learning models over matched-filtering
techniques.

In recent years, convolutional neural network (CNN) and other deep learning
models have been gradually introduced into the area of gravitational-wave (GW)
data processing. Compared with the traditional matched-filtering techniques,
CNN has significant advantages in efficiency in GW signal detection tasks. In
addition, matched-filtering techniques are based on the template bank of the
existing theoretical waveform, which makes it difficult to find GW signals
beyond theoretical expectation. In this paper, based on the task of GW
detection of binary black holes, we introduce the optimization techniques of
deep learning, such as batch normalization and dropout, to CNN models. Detailed
studies of model performance are carried out. Through this study, we recommend
to use batch normalization and dropout techniques in CNN models in GW signal
detection tasks. Furthermore, we investigate the generalization ability of CNN
models on different parameter ranges of GW signals. We point out that CNN
models are robust to the variation of the parameter range of the GW waveform.
This is a major advantage of deep learning models over matched-filtering
techniques.

http://arxiv.org/icons/sfx.gif