A-PINN: Auxiliary physics informed neural networks for forward and inverse problems of nonlinear integro-differential equations

Keyphrases

• Inverse Problem 100%
• Physics-informed Neural Networks 100%
• Forward Problem 100%
• Nonlinear Integro-differential Equation 100%
• Auxiliary Outputs 28%
• Neural Network 21%
• Governing Equation 21%
• Partial Differential Equations 21%
• Integro-differential Equations 21%
• Neural Network Framework 21%
• Volterra Integral Equation 14%
• Nonlinear Volterra Integro-differential Equations 14%
• Neural Network Method 14%
• Output Variable 7%
• First-order 7%
• Ordinary Differential Equations 7%
• Discretization Error 7%
• Approximate Solution 7%
• Accurate Solution 7%
• Learning Paradigm 7%
• Noisy Data 7%
• Benchmark Problems 7%
• Feedforward Neural Network 7%
• Truncation Error 7%
• Nonlinear Partial Differential Equations 7%
• Deep Learning 7%
• Labeled Data 7%
• Multi-output 7%
• Integral Operator 7%
• Physical Data 7%
• Surrogate Model 7%
• Physical Laws 7%
• Nonlinear Fredholm Integral Equation 7%
• Stochastic Partial Differential Equations 7%
• Automatic Differentiation 7%
• Systems of Integro-differential Equations 7%
• Integer Order 7%
• Fractional Partial Differential Equations 7%

Engineering

• Physics Informed Neural Network 100%
• Partial Differential Equation 35%
• Discretization 21%
• Feedforward 7%
• Good Performance 7%
• Nonlinear Partial Differential Equation 7%
• Approximate Solution 7%
• Accurate Solution 7%
• Discretization Error 7%
• Surrogate Model 7%
• Noisy Data 7%
• Benchmark Problem 7%
• Truncation Error 7%
• Deep Learning Method 7%
• Equation System 7%

Chemical Engineering

• Auxiliaries 100%
• Neural Network 100%
• Feedforward Neural Network 5%
• Nonlinear System 5%
• Deep Learning Method 5%