A nonlocal physics-informed deep learning framework using the peridynamic differential operator

Mathematics

• Neural Networks 72%
• Learning 70%
• Differential operator 63%
• Physics 63%
• Framework 44%
• Long-range Interactions 31%
• Gradient 25%
• Network Architecture 16%
• Partial differential equation 16%
• Nonlocal Interactions 15%
• Indentation 15%
• Nonlocality 14%
• Solid Mechanics 14%
• Elasto-plastic 13%
• Performance 13%
• Learning Algorithm 13%
• Mixed Boundary Conditions 12%
• Governing equation 10%
• Numerical Methods 8%
• Simulation 6%
• Derivative 6%
• Range of data 6%

Physics & Astronomy

• differential operators 100%
• learning 83%
• physics 48%
• gradients 16%
• partial differential equations 16%
• solid mechanics 12%
• punches 10%
• inference 9%
• indentation 8%
• performance 7%
• interactions 6%
• boundary conditions 6%

Engineering & Materials Science

• Deep learning 68%
• Physics 66%
• Neural networks 46%
• Mathematical operators 30%
• Partial differential equations 21%
• Indentation 11%
• Network architecture 10%
• Numerical methods 9%
• Mechanics 9%
• Learning algorithms 9%
• Derivatives 9%
• Boundary conditions 8%