A Combined Data-driven and Physics-driven Method for Steady Heat Conduction Prediction using Deep Convolutional Neural Networks.
Hao MaXiangyu HuYuxuan ZhangNils ThuereyOskar J. HaidnPublished in: CoRR (2020)
Keyphrases
- data driven
- objective function
- synthetic data
- detection method
- significant improvement
- cost function
- computational cost
- experimental evaluation
- support vector machine svm
- prediction model
- support vector machine
- computationally efficient
- unsupervised learning
- probabilistic model
- prediction error
- classification method
- prediction algorithm
- mathematical model
- preprocessing
- energy function
- theoretical analysis
- image sequences
- high accuracy
- prior knowledge
- pairwise