cv | Javier Murgoitio-Esandi

2020 - Present

Ph.D. in Mechanical Engineering. Research area - Generative AI

University of Southern California
2017-2019

Master of Research, Research Area - Ocean Engineering

University College London
2015-2016

Master of Science, Civil Engineering

University College London
2011-2015

Bachelor of Engineering, Civil Engineering

University of Basque Country

2023.09 - pres.
Uncertainty Quantification and Machine Learning in Physics Models, Intern

Sandia National Laboratories
- Development of software tools to expand the capabilities of uncertainty quantification in deep learning. Conduct research to improve the understanding of MCMC sampling methods in Bayesian deep learning.

Systems and methods for identification of rare events in biological samples. Patent No. 63/716,845. Issued on November 6, 2024. Role - Co-inventor. Description - The patent relates to a rare event identification method that can be used to determine a patient’s disease state. The method is based on an unsupervised deep learning approach.

NeurIPS
- Dasgupta, A., Murgoitio-Esandi, J., Ray, D., Oberai, A. A. (2023). Conditional score-based generative models for solving physics-based inverse problems. NeurIPS 2023 Workshop on Deep Learning and Inverse Problems. (Accepted)
USNCCM17
- Murgoitio-Esandi, J., Ray, D., Oberai, A. A. (2023). A novel conditional Wasserstein Generative Adversarial Network for inverse problems. U.S. National Congress of Computational Mechanics 17.
WCCM24
- Murgoitio-Esandi, Dasgupta, A., Ramaswamy H., Foo, K., Kennedy, B., Li, R., Zhou, Q., Oberai, A. A. (2024). Inferring mechanical properties of tissue with quantified uncertainty using conditional generative models. World Congress of Computational Mechanics 2024.
WCCM24
- Oberai, A. A., Dasgupta A., Murgoitio-Esandi, J., Ramaswamy, H. (2024). Conditional diffusion models for solving physics-based inverse problems. World Congress of Computational Mechanics 2024.