An unsupervised latent/output physics-informed convolutional-LSTM network for solving partial differential equations using peridynamic differential operator

Engineering

• Partial Differential Equation 100%
• Peridynamics 100%
• Neural Network Architecture 66%
• Term Memory 66%
• Predictive Capability 33%
• Convolutional Neural Network 33%
• Periodic Behavior 33%
• Activation Function 33%
• Field Variable 33%

Keyphrases

• Convolutional LSTM Network 100%
• Novel Activation Functions 33%
• Unsupervised Deep Neural Network 33%