Accelerating Recurrent Neural Networks for Gravitational Wave Experiments

Que, Zhiqiang; Wang, Erwei; Marikar, Umar; Moreno, Eric A.; Ngadiuba, J.; Javed, Hamza; Borzyszkowski, Bartlomiej; Aarrestad, Thea Klaeboe; Lončar, Vladimir; Summers, S.; Pierini, M.; Cheung, Peter Y. K.; Luk, Wayne

doi:10.1109/asap52443.2021.00025

Cited by 18 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, recurrent neural networks (RNNs) based autoencoders have been explored to detect gravitational wave using an unsupervised strategy (Moreno et al, 2021 ). FPGA-based RNNs are also explored to show the potential in low-latency detection of gravitational wave (Que et al, 2021 ). Applications of ML in searches of other types of gravitational waves, such as generic burst and stochastic background, are currently being explored.…”

Section: Exemplars Of Domain Applicationsmentioning

confidence: 99%

Applications and Techniques for Fast Machine Learning in Science

Deiana¹,

Tran²,

Agar³

et al. 2022

Front. Big Data

Self Cite

View full text Add to dashboard Cite

In this community review report, we discuss applications and techniques for fast machine learning (ML) in science—the concept of integrating powerful ML methods into the real-time experimental data processing loop to accelerate scientific discovery. The material for the report builds on two workshops held by the Fast ML for Science community and covers three main areas: applications for fast ML across a number of scientific domains; techniques for training and implementing performant and resource-efficient ML algorithms; and computing architectures, platforms, and technologies for deploying these algorithms. We also present overlapping challenges across the multiple scientific domains where common solutions can be found. This community report is intended to give plenty of examples and inspiration for scientific discovery through integrated and accelerated ML solutions. This is followed by a high-level overview and organization of technical advances, including an abundance of pointers to source material, which can enable these breakthroughs.

show abstract

Section: Exemplars Of Domain Applicationsmentioning

confidence: 99%

Applications and Techniques for Fast Machine Learning in Science

Deiana¹,

Tran²,

Agar³

et al. 2022

Front. Big Data

Self Cite

View full text Add to dashboard Cite

show abstract

“…[44] for real-time data analysis at the Large Hadron Collider. Considering the relatively low computational cost of such an algorithm [43] and the high impact of a potential signal detection by this algorithm, its implementation for LIGO and VIRGO would be certainly be beneficial, despite the fact that the expected detection probability cannot be guaranteed to be high for any signal source.…”

Section: Discussionmentioning

confidence: 99%

“…One should keep in mind that the LSTM model can run on a Field Programmable Gate Array within O(100) nsec, as demonstrated in Ref. [43].…”

Section: Astronomymentioning

confidence: 99%

Source-Agnostic Gravitational-Wave Detection with Recurrent Autoencoders

Moreno¹,

Vlimant²,

Spiropulu³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present an application of anomaly detection techniques based on deep recurrent autoencoders to the problem of detecting gravitational wave signals in laser interferometers. Trained on noise data, this class of algorithms could detect signals using an unsupervised strategy, i.e., without targeting a specific kind of source. We develop a custom architecture to analyze the data from two interferometers. We compare the obtained performance to that obtained with other autoencoder architectures and with a convolutional classifier. The unsupervised nature of the proposed strategy comes with a cost in terms of accuracy, when compared to more traditional supervised techniques. On the other hand, there is a qualitative gain in generalizing the experimental sensitivity beyond the ensemble of pre-computed signal templates. The recurrent autoencoder outperforms other autoencoders based on different architectures. The class of recurrent autoencoders presented in this paper could complement the search strategy employed for gravitational wave detection and extend the reach of the ongoing detection campaigns.

show abstract

“…However, for the applications discussed above we are interested primarily in latencies in the microsecond range, or faster. Some previous work has explored this design space in the context of low-power sparse LSTMs [25], small LSTMs for real-time energy reconstruction [26], RNNs for gravitiation-wave experiments [27], and highly quantized RNNs [28]. In contrast, the work in this paper is focused on general support for both large and small LSTMs and GRUs for problems with a range of latency and device constraints.…”

Section: Related Workmentioning

confidence: 99%

Ultra-low latency recurrent neural network inference on FPGAs for physics applications with hls4ml

Khoda¹,

Rankin²,

Lima³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Recurrent neural networks have been shown to be effective architectures for many tasks in high energy physics, and thus have been widely adopted. Their use in low-latency environments has, however, been limited as a result of the difficulties of implementing recurrent architectures on fieldprogrammable gate arrays (FPGAs). In this paper we present an implementation of two types of recurrent neural network layers-long short-term memory and gated recurrent unit-within the hls4ml framework. We demonstrate that our implementation is capable of producing effective designs for both small and large models, and can be customized to meet specific design requirements for inference latencies and FPGA resources. We show the performance and synthesized designs for multiple neural networks, many of which are trained specifically for jet identification tasks at the CERN Large Hadron Collider.

show abstract

Accelerating Recurrent Neural Networks for Gravitational Wave Experiments

Cited by 18 publications

References 30 publications

Applications and Techniques for Fast Machine Learning in Science

Applications and Techniques for Fast Machine Learning in Science

Source-Agnostic Gravitational-Wave Detection with Recurrent Autoencoders

Ultra-low latency recurrent neural network inference on FPGAs for physics applications with hls4ml

Contact Info

Product

Resources

About