Architectures¶
| Meaning | Efficient at | Major Application | Computation Complexity | Limitation | Advantage | |
|---|---|---|---|---|---|---|
| FC Fully-Connected | Poor scalability for large input sizes Do not capture “intuitive” invariances | |||||
| CNN (Convolutional) | - Require that activations between layers occur only in “local” manner - Treat hidden layers themselves as spatial images - Share weights across all spatial locations | Detecting spatial pattens | Images, Videos | High | Reduce parameter count Capture [some] “natural” invariances | |
| RNN (Recurrent) | Forward-feed, backward-feed, and self-loop is allowed | Detecting dependent/sequential pattens | Time Series | |||
| ResNet (Residual Network) | Time Series | |||||
| U-Net | Basis of diffusion models Segmentation Super-Resolution Diffusion Models | |||||
| PINN (Physics-Informed) | ||||||
| Lagrangian | ||||||
| Deep Operator | ||||||
| Fourier Neural Operator | ||||||
| Graph Neural Networks |