Welcome to SurKit’s documentation!

A surrogate model is a simplified model that can replace a complex or high-fidelity model in engineering problems. Surrogate models can reduce the computational cost and time of evaluating the original model, and facilitate the optimization and approximation processes. SurKit allows users who are unfamiliar with neural networks to get started quickly by selecting the type of surrogate model and providing parameters to automatically generate and train surrogate models.

User Guide

• Install and Setup
  • Installation

Getting Started

• Solve Function
  • Chose Backend
  • Define Formula
  • Data Generation
  • Define Model
  • Define Training
  • Load Model
  • Inference
  • Complete Code
• Uncertainty Quantification
  • Neural Network Ensemble
  • Bayesian Neural Network
  • Complete Code

API Reference

If you are looking for information on a specific function, class or method, this part of the documentation is for you.

API

• surkit.backend package
  • Submodules
  • surkit.backend.backend module
  • surkit.backend.jax_bkd module
  • surkit.backend.oneflow_bkd module
  • surkit.backend.pytorch_bkd module
  • Module contents
• surkit.data package
  • Submodules
  • surkit.data.dataset module
  • surkit.data.processing module
  • surkit.data.sampling module
  • Module contents
• surkit.conditions package
  • Submodules
  • surkit.conditions.hard_condition module
  • surkit.conditions.icbc module
  • surkit.conditions.icbc2d module
  • Module contents
• surkit.pde package
  • Submodules
  • surkit.pde.pde module
  • Module contents
• surkit.nn.pytorch package
  • Submodules
  • surkit.nn.pytorch.activations module
  • surkit.nn.pytorch.bayes_cnn module
  • surkit.nn.pytorch.bayes_dense_ed module
  • surkit.nn.pytorch.bayes_layer module
  • surkit.nn.pytorch.bayes_nn module
  • surkit.nn.pytorch.cnn module
  • surkit.nn.pytorch.dense_ed module
  • surkit.nn.pytorch.fnn module
  • surkit.nn.pytorch.initializers module
  • surkit.nn.pytorch.nn_ensemble module
  • surkit.nn.pytorch.pooling module
  • surkit.nn.pytorch.transform module
  • Module contents
• surkit.nn.oneflow package
  • Submodules
  • surkit.nn.oneflow.activations module
  • surkit.nn.oneflow.bayes_cnn module
  • surkit.nn.oneflow.bayes_dense_ed module
  • surkit.nn.oneflow.bayes_layer module
  • surkit.nn.oneflow.bayes_nn module
  • surkit.nn.oneflow.cnn module
  • surkit.nn.oneflow.dense_ed module
  • surkit.nn.oneflow.fnn module
  • surkit.nn.oneflow.initializers module
  • surkit.nn.oneflow.nn_ensemble module
  • surkit.nn.oneflow.pooling module
  • surkit.nn.oneflow.transform module
  • surkit.nn.oneflow.utils module
  • Module contents
• surkit.nn.jax package
  • Submodules
  • surkit.nn.jax.activations module
  • surkit.nn.jax.bayes_cnn module
  • surkit.nn.jax.bayes_dense_ed module
  • surkit.nn.jax.bayes_layer module
  • surkit.nn.jax.bayes_nn module
  • surkit.nn.jax.cnn module
  • surkit.nn.jax.dense_ed module
  • surkit.nn.jax.fnn module
  • surkit.nn.jax.initializers module
  • surkit.nn.jax.nn_ensemble module
  • surkit.nn.jax.pooling module
  • surkit.nn.jax.transform module
  • surkit.nn.jax.utils module
  • Module contents
• surkit.losses package
  • Submodules
  • surkit.losses.losses_jax module
  • surkit.losses.losses_oneflow module
  • surkit.losses.losses_pytorch module
  • Module contents
• surkit.optimizer package
  • Submodules
  • surkit.optimizer.optimizer_jax module
  • surkit.optimizer.optimizer_oneflow module
  • surkit.optimizer.optimizer_pytorch module
  • Module contents
• surkit.train package
  • Submodules
  • surkit.train.train_jax module
  • surkit.train.train_oneflow module
  • surkit.train.train_pytorch module
  • Module contents

Indices and tables

• Index

• Module Index

• Search Page