Bio


I am a PhD student in the Institute for Computational and Mathematical Engineering (ICME). I was born and I received my education in Spain. I received my two Bachelor's degrees in Industrial Technology Engineering and in Civil Engineering at Universitat Politècnica de Catalunya (UPC) in Barcelona. In 2014 I moved for 6 months to France to finish my Bachelor's degree in Civil Engineering at Ecole Centrale de Nantes. Next, I returned to Barcelona to course a MSc in Civil Engineering at UPC and gain work experience in civil engineering. My research interests lie in the area of computational engineering.

Honors & Awards


  • Stanford Graduate Fellowship in Science & Engineering, Stanford University (2016)
  • La Caixa Graduate Fellowship, Obra Social "La Caixa" (07/12/2016)
  • Award to the best academic record for dual degree program at CFIS, Universitat Politècnica de Catalunya (12/18/2015)

Education & Certifications


  • MSc, Universitat Politècnica de Catalunya (UPC), Civil Engineering (2016)
  • BSc, Universitat Politècnica de Catalunya (UPC), Mechanical Engineering (2015)
  • BSc, Universitat Politècnica de Catalunya (UPC), Civil Engineering (2014)

Work Experience


  • Civil engineer, SENER (7/1/2015 - 7/1/2016)

    Location

    Barcelona

  • Research intern, ICFO (The Institute of Photonic Sciences) (7/13/2014 - 9/30/2014)

    Location

    Barcelona

All Publications


  • Meta-learning pseudo-differential operators with deep neural networks JOURNAL OF COMPUTATIONAL PHYSICS Feliu-Faba, J., Fan, Y., Ying, L. 2020; 408
  • RECURSIVELY PRECONDITIONED HIERARCHICAL INTERPOLATIVE FACTORIZATION FOR ELLIPTIC PARTIAL DIFFERENTIAL EQUATIONS COMMUNICATIONS IN MATHEMATICAL SCIENCES Feliu-Faba, J., Ho, K. L., Ying, L. 2020; 18 (1): 91–108
  • A continuous-discontinuous model for crack branching INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING Tamayo-Mas, E., Feliu-Faba, J., Casado-Antolin, M., Rodriguez-Ferran, A. 2019; 120 (1): 86–104

    View details for DOI 10.1002/nme.6125

    View details for Web of Science ID 000483870600004

  • A multiscale neural network based on hierarchical nested bases RESEARCH IN THE MATHEMATICAL SCIENCES Fan, Y., Feliu-Faba, J., Lin, L., Ying, L., Zepeda-Nunez, L. 2019; 6 (2)
  • Learning Twitter User Sentiments on Climate Change with Limited Labeled Data Koenecke, A., Feliu-Fabà, J. arxiv. 2019
  • A multiscale neural network based on hierarchical nested bases Fan, Y., Feliu-Fabà, J., Lin, L., Ying, L., Zepeda-Núñez, L. arXiv. 2018

    Abstract

    n recent years, deep learning has led to impressive results in many fields. In this paper, we introduce a multi-scale artificial neural network for high-dimensional non-linear maps based on the idea of hierarchical nested bases in the fast multipole method and the H2-matrices. This approach allows us to efficiently approximate discretized nonlinear maps arising from partial differential equations or integral equations. It also naturally extends our recent work based on the generalization of hierarchical matrices [Fan et al. arXiv:1807.01883] but with a reduced number of parameters. In particular, the number of parameters of the neural network grows linearly with the dimension of the parameter space of the discretized PDE. We demonstrate the properties of the architecture by approximating the solution maps of non-linear Schr{\"o}dinger equation, the radiative transfer equation, and the Kohn-Sham map.

  • Multiscale modelling for the thermal creep analysis of PCM concrete Energy and Buildings Mohaine, S., et al 2016; 131: 14