Developing a victorious strategy to the second strong gravitational lensing data challenge

Fraga, Bernardo Machado de Oliveira; Dias, Luciana Olivia; Schubert, Patrick; Valentin, Manuel Blanco; Furlanetto, C.; Makler, M.; Teles, K; Albuquerque, Marcelo P. de; Metcalf, R. Benton

doi:10.1093/mnras/stac2047

Cited by 10 publications

(8 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Notably, the transformer models demonstrate exceptional performance compared to the CNNs mentioned in prior studies, highlighting the adaptability of transformers in the context of strong lens detection. For a comprehensive understanding of the datasets, please refer to Metcalf et al (2019); Bom et al (2022) for Bologna Lens Challenge 1 and 2, and Euclid Collaboration (2023) for the Euclid simulation datasets.…”

Section: Results and Conclusionmentioning

confidence: 99%

Strong Lens Detection 2.0: Machine Learning and Transformer Models

Thuruthipilly

2022

Proc. IAU

View full text Add to dashboard Cite

Upcoming large-scale surveys like LSST are expected to uncover approximately 105 strong gravitational lenses within massive datasets. Traditional manual techniques are too time-consuming and impractical for such volumes of data. Consequently, machine learning methods have emerged as an alternative. In our prior work (Thuruthipilly et al. 2022), we introduced a self-attention-based machine learning model (transformers) for detecting strong gravitational lenses in simulated data from the Bologna Lens Challenge. These models offer advantages over simpler convolutional neural networks (CNNs) and competitive performance compared to state-of-the-art CNN models. We applied this model to the datasets from Bologna Lens Challenge 1 and 2 and simulated data on Euclid.

show abstract

Section: Results and Conclusionmentioning

confidence: 99%

Strong Lens Detection 2.0: Machine Learning and Transformer Models

Thuruthipilly

2022

Proc. IAU

View full text Add to dashboard Cite

show abstract

“…The model considers the human body as a skeleton-connected multi-rigid-body system and simulates real human body movements by modeling the limb structure and skeletal muscle mechanics of the real human body. Skeletal muscles in the human body drive bone and joint movements through muscle contraction and relaxation, and the composition of skeletal muscles is shown in Figure 1 [28,29]. Skeletal muscle consists of muscle fibers, as shown in Figure 1.…”

Section: Human Motion Control Model Based On Muscle Force and Stage P...mentioning

confidence: 99%

Motor Interaction Control Based on Muscle Force Model and Depth Reinforcement Strategy

Liu,

Zhang,

Lee

et al. 2024

Biomimetics

View full text Add to dashboard Cite

The current motion interaction model has the problems of insufficient motion fidelity and lack of self-adaptation to complex environments. To address this problem, this study proposed to construct a human motion control model based on the muscle force model and stage particle swarm, and based on this, this study utilized the deep deterministic gradient strategy algorithm to construct a motion interaction control model based on the muscle force model and the deep reinforcement strategy. Empirical analysis of the human motion control model proposed in this study revealed that the joint trajectory correlation and muscle activity correlation of the model were higher than those of other comparative models, and its joint trajectory correlation was up to 0.90, and its muscle activity correlation was up to 0.84. In addition, this study validated the effectiveness of the motion interaction control model using the depth reinforcement strategy and found that in the mixed-obstacle environment, the model’s desired results were obtained by training 1.1 × 103 times, and the walking distance was 423 m, which was better than other models. In summary, the proposed motor interaction control model using the muscle force model and deep reinforcement strategy has higher motion fidelity and can realize autonomous decision making and adaptive control in the face of complex environments. It can provide a theoretical reference for improving the effect of motion control and realizing intelligent motion interaction.

show abstract

“…For example, Madireddy et al (2019) proposed a complete deep learning based pipeline including detection and classification of lenses followed by a modelling phase. Bom et al (2019) apply Residual Neural Networks to simulated images of the Dark Energy Survey to predict Einstein Radius, lens velocity dispersion and lens redshift within 10–15%. See also Schuldt et al (2021) for similar conclusions on simulated Hubble Space Telescope and Hyper Suprime-Cam Survey images.…”

Section: Deep Learning For Inferring Physical Properties Of Galaxiesmentioning

confidence: 99%

The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys

Huertas-Company

Lanusse²

2023

Publ. Astron. Soc. Aust.

View full text Add to dashboard Cite

The amount and complexity of data delivered by modern galaxy surveys has been steadily increasing over the past years. New facilities will soon provide imaging and spectra of hundreds of millions of galaxies. Extracting coherent scientific information from these large and multi-modal data sets remains an open issue for the community and data-driven approaches such as deep learning have rapidly emerged as a potentially powerful solution to some long lasting challenges. This enthusiasm is reflected in an unprecedented exponential growth of publications using neural networks, which have gone from a handful of works in 2015 to an average of one paper per week in 2021 in the area of galaxy surveys. Half a decade after the first published work in astronomy mentioning deep learning, and shortly before new big data sets such as Euclid and LSST start becoming available, we believe it is timely to review what has been the real impact of this new technology in the field and its potential to solve key challenges raised by the size and complexity of the new datasets. The purpose of this review is thus two-fold. We first aim at summarising, in a common document, the main applications of deep learning for galaxy surveys that have emerged so far. We then extract the major achievements and lessons learned and highlight key open questions and limitations, which in our opinion, will require particular attention in the coming years. Overall, state-of-the-art deep learning methods are rapidly adopted by the astronomical community, reflecting a democratisation of these methods. This review shows that the majority of works using deep learning up to date are oriented to computer vision tasks (e.g. classification, segmentation). This is also the domain of application where deep learning has brought the most important breakthroughs so far. However, we also report that the applications are becoming more diverse and deep learning is used for estimating galaxy properties, identifying outliers or constraining the cosmological model. Most of these works remain at the exploratory level though which could partially explain the limited impact in terms of citations. Some common challenges will most likely need to be addressed before moving to the next phase of massive deployment of deep learning in the processing of future surveys; for example, uncertainty quantification, interpretability, data labelling and domain shift issues from training with simulations, which constitutes a common practice in astronomy.

show abstract

Developing a victorious strategy to the second strong gravitational lensing data challenge

Cited by 10 publications

References 87 publications

Strong Lens Detection 2.0: Machine Learning and Transformer Models

Strong Lens Detection 2.0: Machine Learning and Transformer Models

Motor Interaction Control Based on Muscle Force Model and Depth Reinforcement Strategy

The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys

Contact Info

Product

Resources

About