From f34bb9de7357f52c05142b5f269c1cedff36d31e Mon Sep 17 00:00:00 2001 From: mastoffel Date: Wed, 18 Dec 2024 09:22:28 +0000 Subject: [PATCH] change docs --- docs/index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/index.md b/docs/index.md index ac4c6dd8..d8ec9907 100644 --- a/docs/index.md +++ b/docs/index.md @@ -1,4 +1,4 @@ -# Welcome to `AutoEmulate` +# Welcome to `AutoEmulate`! `AutoEmulate` is designed to be an easy, low-code pipeline to create emulators for complex simulations. At it's core, `AutoEmulate`'s `compare()` function implements a typical machine learning workflow including data processing, selecting a good emulator model, optimising model parameters and evaluating its test-set performance. Emulators range from classical models like *Radial Basis Functions* and *Second Order Polynomials* to popular machine learning methods like *Gradient Boosting* and *Support Vector Machines*, as well as modern PyTorch-based models like *Neural Processes* and *Multitask Gaussian Processes*. All default parameters and search spaces for hyperparameter optimisation are chosen to be appropriate for typical emulation problems, i.e. small-ish datasets (100s or 1000s of datapoints) with potentially many features and outputs. We've also implemented Global Sensitivity Analysis as a common use-case for emulators, and plan to add more applications in the future.