Generative Models
Diffusion models, generative adversarial networks, and adversarial autoencoders for structured and temporal data.
PhD Candidate in Computer Science
MohammadReza “Sam” EskandariNasab is a machine learning researcher at Utah State University specializing in generative modeling, multivariate time-series analysis, and trustworthy AI for scientific applications.
Research areas
Diffusion models, generative adversarial networks, and adversarial autoencoders for structured and temporal data.
Machine learning methods for solar-flare forecasting and multimodal analysis of space-weather observations.
Representation learning, classification, generation, and domain adaptation for multivariate time-series data.
Deep learning for EEG, auditory attention detection, and the analysis of complex neurophysiological signals.
Academic and professional experience
Utah State University · Logan, Utah
Utah State University · NSF-Funded Project
Education
Utah State University · Logan, Utah
Research: generative models, multimodal learning, time-series analysis, and solar-flare prediction.
Advisor: Dr. Shah Muhammad Hamdi
Utah State University · Logan, Utah
Thesis: Supervised Generative Adversarial Networks for Time Series Generation in Embedding Space.
University of Zanjan · Zanjan, Iran
Capstone: full-stack automotive marketplace with a dynamic reputation-weighted pricing algorithm.
Academic profile
MohammadReza EskandariNasab, professionally known as Sam Alexanders, is a PhD candidate in Computer Science at Utah State University.
His research agenda centers on generative machine learning for structured temporal data, with applications in space weather and biomedical signal processing. He is committed to an academic career that integrates high-impact scholarship, inclusive teaching, reproducible research, and professional service.
Reviewer for leading journals including Information Fusion, Artificial Intelligence, Neurocomputing, and the IEEE Journal of Biomedical and Health Informatics; conference volunteer for IEEE ICDM and IEEE Big Data.
Research collaboration · Academic opportunities · Student mentorship
Begin a scholarly