w_MATHMODE

Group on Applied Mathematical Modeling, Statistics, and Optimization (MATHMODE)

 

Department (s)
Mathematics, Applied Mathematics, Computer Sciences and Artificial Intelligence

Knowledge area
Applied Mathematics, Statistics, Artificial Intelligence, Scientific Computing
PI: David Pardo Co-PI: Inmaculada Arostegui

Members

Mikel Lezaun, Carlos Gorria, Irantzu Barrio, Urtzi Ayesta, Ander Murua, Elisabete Alberdi, Joseba Makazaga, Javier del Ser, Josu Doncel, Mikel Antoñana, Javier Omella, Amaia Iparraguirre, Ana Fernández-Navamuel, Carlos Uriarte, Oscar Rodríguez, Felipe Caro

Keywords

Deep Learning, Statistics, Finite Elements, Simulation, Inversion, Health, Geosciences, Optimization.

Description

  1. We exploit deep learning concepts to design innovative efficient and robust algorithms able to solve inverse problems arising in geophysics, structural health monitoring, and offshore wind energy.
  2. We develop statistical methodology oriented to the resolution of complexities derived from scientific research in the areas of experimental sciences, biosanitary and industry, among others. 
  3. We employ statistics to validate and efficiently analyze real data. We promote the transfer of the research in statistics to biomedical and experimental fields.
  4. We contribute to the advances in real-world industry and healthcare, by solving the arising mathematical problems with the proposed methods.
  5. Advanced numerical methods for time integration of differential equations. We to analyze, design, and implement numerical integration methods for time evolution problems governed by differential equations.
  6. Applied optimization problems. We carry out projects with companies, making technology transfer in the fields of optimization, simulation, operational research, and statistics.

Lines of Research

Deep Learning, Statistics, Numerical Methods, Time integration problems, Applied optimization problems, Advances in real-world industry, and Healthcare.

Equipment

Server with 4 GPU Quadro V100 Graphics Cards and 512 GB RAM.

Website link

www.mathmode.science

Contact

david.pardo@ehu.eus