Credits: 4 (3-0-2)
Description
Plied math and machine learning basics, deep feedforward network, regularization for deep learning, optimization for training deep learning, convolutional network, recurrent neural network.
Physics informed deep learning in computational mechanics, residual based approach, energy approach, time-discretization in physics informed deep learning, deep learning for inverse problems in mechanics, physics informed deep learning for stochastic dynamic/ mechanics problems.
Application in mechanics (Practical Component): Data-driven deep learning for stochastic mechanics. Data-driven deep learning for solving inverse problems, Physics informed deep learning for fracture mechanics, Physics informed deep learning for reliability analysis, Physics informed deep learning for ID phase-field equation, learning parameters of Navier stokes equation and constitutive relations using physics informed deep learning.