AmeyaJagtap / Rowdy_Activation_FunctionsLinks
We propose Deep Kronecker Neural Network, which is a general framework for neural networks with adaptive activation functions. In particular we proposed Rowdy activation functions that inject sinusoidal fluctuations thereby allows the optimizer to exploit more and train the network faster. Various test cases ranging from function approximation, …
☆12Updated 2 years ago
Alternatives and similar repositories for Rowdy_Activation_Functions
Users that are interested in Rowdy_Activation_Functions are comparing it to the libraries listed below
Sorting:
- ☆64Updated 3 years ago
- Reliable extrapolation of deep neural operators informed by physics or sparse observations☆28Updated 2 years ago
- Sparse Physics-based and Interpretable Neural Networks☆52Updated 4 years ago
- This is the implementation of the RecFNO.☆25Updated 2 years ago
- Physics-informed deep super-resolution of spatiotemporal data☆48Updated 2 years ago
- Official implementation of "PhyGNNet: Solving spatiotemporal PDEs with Physics-informed Graph Neural Network"☆52Updated 2 years ago
- POD-PINN code and manuscript☆55Updated last year
- PDE Preserved Neural Network☆58Updated 6 months ago
- PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parametric PDEs on Irregular Domain☆88Updated 4 years ago
- Python codes for Locally Adaptive Activation Function (LAAF) used in deep neural networks. Please cite this work as "A D Jagtap, K Kawa…☆43Updated 2 years ago
- Physics Informed Fourier Neural Operator☆23Updated last year
- Source code of "Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems."☆75Updated 6 months ago
- ☆54Updated 3 years ago
- Source code of 'Deep transfer operator learning for partial differential equations under conditional shift'.☆74Updated 2 years ago
- U-FNO - an enhanced Fourier neural operator-based deep-learning model for multiphase flow☆155Updated last year
- GCA-ROM is a library which implements graph convolutional autoencoder architecture as a nonlinear model order reduction strategy.☆36Updated last week
- ☆37Updated 2 years ago
- Physics-encoded recurrent convolutional neural network☆46Updated 3 years ago
- Surrogate Modeling for Fluid Flows Based on Physics-Constrained Label-Free Deep Learning☆92Updated 2 years ago
- Separabale Physics-Informed DeepONets in JAX☆15Updated 11 months ago
- ☆10Updated 2 years ago
- ☆39Updated last year
- Learning two-phase microstructure evolution using neural operators and autoencoder architectures☆25Updated last year
- ☆52Updated 11 months ago
- Pytorch implementation of Bayesian physics-informed neural networks☆65Updated 4 years ago
- 2nd Order Wave Equation PINN Solution/ TensorFlow & PyTorch☆28Updated 3 years ago
- Towards Physics-informed Deep Learning for Turbulent Flow Prediction☆27Updated 4 years ago
- Semi-supervised Invertible Neural Operators for Bayesian Inverse Problems☆14Updated last year
- Physics-Constrained Bayesian Neural Network for Fluid Flow Reconstruction with Sparse and Noisy Data☆49Updated 5 years ago
- Deep finite volume method☆22Updated last year