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)
- Physics-Guided Loss Function
- Physics-Guided Initialization
- Physics-Guided Network Design
- Residual modeling
- 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.
Professores
Alexandre Gonçalves Evsukoff
Alvaro L. G. A. Coutinho
Créditos / CH (Credits/ Workload)
45h