This repository contains several key models written in PyTorch.
- NN (Neural Network)
- Standard fully connected neural networks
- MFNN (Multi-fidelity Neural Network)
- Three standard neural networks coupled to fit high-fidelity data, high-fidelity data and their linear combination.
- PINNs (Physical-informed Neural Networks)
- Physical-informed neural network for solving partial differential equations, e.g., Allen-Cahn equation(1D time-dependent and 2D equilibrium state)
- CNN (Convolutional Neural Network)
- Convolutional neural network(Decoder)
Proof of Concept are listed below:
- DynNet (Dynamic-graph Network)
- Fully-connected neural network to demonstrate the concept of dynamic graph.
- Gradient (Automatic Differentiation)
- Calculate gradient in PyTorch