Probabilistic parameter estimation using a Gaussian mixture density network: application to X-ray reflectivity data curve fitting

Kim, Kook Tae; Lee, Dong Ryeol

doi:10.1107/s1600576721009043

Cited by 7 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to confirm the effect of Gd and uncover the additive roles of the proximity-induced magnetic moments with two different origins, we investigate the interfacial structural and magnetic properties of the Pt layer using x-ray reflectivity (XRR) and XRMR. First, XRR is used to determine the structural depth profile 36 – 38 . XRR data are quantitatively analyzed by fitting it with multiple parameters such as the film thickness, density, and interfacial roughness (Fig.…”

Section: Resultsmentioning

confidence: 99%

Additive roles of antiferromagnetically coupled elements in the magnetic proximity effect in the GdFeCo/Pt system

Kee,

Kim,

Lee

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

Interfacial magnetic interactions between different elements are the origin of various spin-transport phenomena in multi-elemental magnetic systems. We investigate the coupling between the magnetic moments of the rare-earth, transition-metal, and heavy-metal elements across the interface in a GdFeCo/Pt thin film, an archetype system to investigate ferrimagnetic spintronics. The Pt magnetic moments induced by the antiferromagnetically aligned FeCo and Gd moments are measured using element-resolved x-ray measurements. It is revealed that the proximity-induced Pt magnetic moments are always aligned parallel to the FeCo magnetic moments, even below the ferrimagnetic compensation temperature where FeCo has a smaller moment than Gd. This is understood by a theoretical model showing distinct effects of the rare-earth Gd 4f and transition-metal FeCo 3d magnetic moments on the Pt electronic states. In particular, the Gd and FeCo work in-phase to align the Pt moment in the same direction, despite their antiferromagnetic configuration. The unexpected additive roles of the two antiferromagnetically coupled elements exemplify the importance of detailed interactions among the constituent elements in understanding magnetic and spintronic properties of thin film systems.

show abstract

Section: Resultsmentioning

confidence: 99%

Additive roles of antiferromagnetically coupled elements in the magnetic proximity effect in the GdFeCo/Pt system

Kee,

Kim,

Lee

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is addressed in existing implementations, e.g. by restricted parameter ranges (Doucet et al, 2021;Mironov et al, 2021;Greco et al, 2021), a focus on identification of different families of SLD profiles based on symmetry (Carmona Loaiza & Raza, 2021), employing mixture density models (Kim & Lee, 2021), using variational autoencoders (Andrejevic et al, 2022) or neural operators (Munteanu et al, 2023) and convolutional neural networks (Aoki et al, 2021). The approach chosen for this work distinguishes itself from previous implementations by allowing or accommodating prior knowledge (e.g.…”

Section: Methodsmentioning

confidence: 99%

Closing the loop: autonomous experiments enabled by machine-learning-based online data analysis in synchrotron beamline environments

Pithan,

Starostin,

Mareček

et al. 2023

J Synchrotron Radiat

View full text Add to dashboard Cite

Recently, there has been significant interest in applying machine-learning (ML) techniques to the automated analysis of X-ray scattering experiments, due to the increasing speed and size at which datasets are generated. ML-based analysis presents an important opportunity to establish a closed-loop feedback system, enabling monitoring and real-time decision-making based on online data analysis. In this study, the incorporation of a combined one-dimensional convolutional neural network (CNN) and multilayer perceptron that is trained to extract physical thin-film parameters (thickness, density, roughness) and capable of taking into account prior knowledge is described. ML-based online analysis results are processed in a closed-loop workflow for X-ray reflectometry (XRR), using the growth of organic thin films as an example. Our focus lies on the beamline integration of ML-based online data analysis and closed-loop feedback. Our data demonstrate the accuracy and robustness of ML methods for analyzing XRR curves and Bragg reflections and its autonomous control over a vacuum deposition setup.

show abstract

“…Evaluation of the impact of the bias and class imbalance problems on the possible favorable impact per each group was done using the IBM AI Fairness 360 Toolkit [37]. The toolkit can help to examine, report, and mitigate discrimination and bias in machine learning systems, supporting the entire application lifecycle.…”

Section: Class Imbalance and Bias Evaluationmentioning

confidence: 99%

Can AI See Bias in X-ray Images?

Szankin

Kwaśniewska²

2022

IJNDI

View full text Add to dashboard Cite

Article Can AI See Bias in X-ray images? Kwasniewska Alicja *, and Szankin Maciej * 1 SiMa Technologies Inc. 226 Airport Parkway, Suite 550 San Jose, CA 95110, United States 2 Intel Corporation 16409 W Bernardo Dr Suite 100, San Diego, CA 92127, United States * Correspondence: alicja.kwasniewska@sima.ai; maciej.szankin@intel.com Received: 8 November 2022 Accepted: 13 November 2022 Published: 22 December 2022 Abstract: Recent advances in artificial intelligence (AI) have shown promising results in various image-based systems, improving accuracy and throughput, while reducing latency. All these factors are crucial in healthcare and have generated increased interest in this technology. However, there are also multiple challenges integrating AI in existing systems, such as poor explainability, data imbalance and bias. These challenges affect the reliability of the neural networks used in AI applications. The limitations may significantly affect the quality and cost of medical care by introducing false positive diagnosis. The false positives subsequently lead to increased stress in patients and necessitate additional testing and procedures. Lack of rich data representing all socio-economic groups can also undermine reliable decisions for underrepresented groups. Although various studies discussed techniques that may help with bias mitigation, to the best of our knowledge, no practical experiments have been conducted so far that compare different reweighting approaches using convolutional neural networks (CNN). This work focuses on in-depth explanatory analysis of chest X-ray datasets to understand and quantify the problem of class imbalance and bias. After that, various topologies of binary classifications are compared, followed by practical applications of loss reweighting techniques and comparison of their influence of privileged, underprivileged, and overall population. Experiments proved that high classification accuracy can be achieved using an efficient model topology suitable for embedded devices, making it possible to run locally without the need for cloud processing. Preliminary results showed that performance of the model for the underprivileged class can be improved by 15% if proper weighting factors are obtained and applied during the training procedure.

show abstract

Probabilistic parameter estimation using a Gaussian mixture density network: application to X-ray reflectivity data curve fitting

Cited by 7 publications

References 20 publications

Additive roles of antiferromagnetically coupled elements in the magnetic proximity effect in the GdFeCo/Pt system

Additive roles of antiferromagnetically coupled elements in the magnetic proximity effect in the GdFeCo/Pt system

Closing the loop: autonomous experiments enabled by machine-learning-based online data analysis in synchrotron beamline environments

Can AI See Bias in X-ray Images?

Contact Info

Product

Resources

About