DNN2: A hyper-parameter reinforcement learning game for self-design of neural network based elasto-plastic constitutive descriptions
Journal article   Open access  Peer reviewed

DNN2: A hyper-parameter reinforcement learning game for self-design of neural network based elasto-plastic constitutive descriptions

Alexander Fuchs, Yousef Heider, Kun Wang, WaiChing Sun and Michael Kaliske
Computers & structures, Vol.249, p.106505
06/2021

Abstract and subjects

Data-driven computational mechanics Hyper-parameter optimization Meta-modeling Multiscale modeling Neural network constitutive law Reinforcement learning
url
https://www.sciencedirect.com/science/article/am/pii/S0045794921000274View
Published (Version of record) Open

Metrics

3 Record Views

Details