CPC815 - Physics-Based Machine Learning

Objetivos

Estudo dirigido para explorar os resultados recentes de modelos de machine learning combinados com equações de modelos físicos. O conteúdo será abordado na forma de seminários, realziados pelos professores, convidados e alunos.

Ementa (Syllabus)

  1. .Physics-Guided Loss Function
  2. Physics-Guided Initialization
  3. Physics-Guided Network Design
  4. Residual modeling
  5. Hybrid Physics-ML Models

 

Bibliografia (Bibliography

[1] Deep Learning, Yoshua Bengio, Ian Goodfellow, Aaron Courville, MIT Press

[2] Representation Learning: A Review and New Perspectives, Yoshua Bengio, Aaron Courville, Pascal Vincent, Arxiv, 2012.

[3] Willard, X. Jia, S. Xu, M. Steinbach, V. Kumar. Integrating Physics-Based Modeling with Machine Learning: A Survey.  arXiv:2003.04919

[4] LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. “Deep learning.” Nature 521, no. 7553 (2015): 436-444

[5] S. Brunton, J.N. Kutz, Data-Driven Science and Engineering, Machine Learning, Dynamical System, and Control, 2019..

 

Professor

  • Alexandre Gonçalves Evsukoff
  • Alvaro L. G. A. Coutinho

 

Créditos / CH (Credits/ Workload)

3.0 / 45h 

Imprimir