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
• Physics-Guided Loss Function
• Physics-Guided Initialization
• Physics-Guided Network Design
• Residual modeling
• Hybrid Physics-ML Models
Bibliografia
• Deep Learning, Yoshua Bengio, Ian Goodfellow, Aaron Courville, MIT Press
• Representation Learning: A Review and New Perspectives, Yoshua Bengio, Aaron Courville, Pascal Vincent, Arxiv, 2012.
• Willard, X. Jia, S. Xu, M. Steinbach, V. Kumar. Integrating Physics-Based Modeling with Machine Learning: A Survey. arXiv:2003.04919
• LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. “Deep learning.” Nature 521, no. 7553 (2015): 436-444
• S. Brunton, J.N. Kutz, Data-Driven Science and Engineering, Machine Learning, Dynamical System, and Control, 2019.
Créditos
3.0/45h
Professor
Alexandre Gonçalves Evsukoff
Alvaro L. G. A. Coutinho
