Journal of Machine Learning for Modeling and Computing

Journal of Machine Learning for Modeling and Computing JMLMC publishes the latest research in deep learning, engineering, AI, neural networks and more!

✨ As conversations about equity in STEM education grow louder (and in many places, more contested) this 2001 article ...
05/29/2026

✨ As conversations about equity in STEM education grow louder (and in many places, more contested) this 2001 article from our journal reminds us that the data has been speaking for decades. Research published in the Journal of Women and Minorities in Science and Engineering explored how gender and race/ethnicity shape the science motivation and self-efficacy beliefs of middle school students, revealing meaningful differences across groups at a pivotal stage in academic development. The study found that self-efficacy, a student's belief in their own ability to succeed, emerged as a critical predictor of science achievement, but the factors shaping that belief were not the same for every student. At a time when DEI programs in K–12 education are being rolled back across the country, findings like these raise urgent questions: what happens to students whose paths to science confidence are already less supported when the structural investments designed to reach them disappear? The full picture is more nuanced,and more important, than a headline can capture.

Read the full article here: http://dl.begellhouse.com/journals/00551c876cc2f027,2615af3e3226be3e,6fffc62e1bcd9212.html

🫁 New from Thermopedia: AI-Driven Digital Twins for Real-Time Lung Mechanics charts a path from computationally intensiv...
05/15/2026

🫁 New from Thermopedia: AI-Driven Digital Twins for Real-Time Lung Mechanics charts a path from computationally intensive fluid-structure interaction (FSI) simulations to patient-ready clinical tools, using AI and reduced-order models to deliver instantaneous, personalized predictions of respiratory function at the bedside.

Authored by Syed Anas Nisar and Debjyoti Banerjee of Texas A&M University, this work bridges computational fluid dynamics, machine learning, and clinical medicine. By training neural networks on high-fidelity FSI data, including convolutional models and physics-consistent neural FSI frameworks, the authors create digital twins capable of mapping patient anatomy directly to airway mechanics in seconds, not hours.

A standout example of the interdisciplinary research Begell House champions: forging connections across engineering, AI, and biomedicine to open new pathways toward transdisciplinary discoveries and next-generation practices in personalized respiratory care and precision medicine.

Read the full article to explore the computational strategies enabling bedside decision support: 🔗 https://thermopedia.com/content/10477/?utm_medium=email&utm_source=ctct

🔬 New from Thermopedia: Revisiting the classic differentially heated square cavity benchmark, this article explores how ...
04/16/2026

🔬 New from Thermopedia: Revisiting the classic differentially heated square cavity benchmark, this article explores how sparse data and physics-informed machine learning can transform the prediction of buoyancy-driven flows across a wide range of Rayleigh numbers.

Authored by Sai Ganga, Madhukar M. Rao, and Akshai K. Runchal of Analytic Computational Research Inc. (ACRi), the work demonstrates how a hybrid neural network, enhanced with embedded governing equations, achieves improved accuracy and physical consistency over purely data-driven models, even with limited CFD training data.
Read the full article to explore how parametric surrogate models and PINNs can reduce computational cost while preserving fluid mechanics fundamentals:

🔗 https://thermopedia.com/content/10470/?utm_medium=email&utm_source=ctct

Address

50 North Street
Danbury, CT
06810

Telephone

+12034566161

Website

Alerts

Be the first to know and let us send you an email when Journal of Machine Learning for Modeling and Computing posts news and promotions. Your email address will not be used for any other purpose, and you can unsubscribe at any time.

Contact The Business

Send a message to Journal of Machine Learning for Modeling and Computing:

Shortcuts

Share

Category