Update description.

README.md

@@ -10,10 +10,12 @@ Learning function operators with neural networks.
 [![Test](https://github.com/aai-institute/continuiti/actions/workflows/test.yml/badge.svg)](https://github.com/aai-institute/continuiti/actions/workflows/test.yml)
 </div>
 
-**continuiti** is a Python package for machine learning on function operators.
-It implements various neural operator architectures (e.g., DeepONets),
-physics-informed loss functions to train based on PDEs, and a collection of
-examples and benchmarks.
+**continuiti** is a Python package for deep learning on function operators with
+a focus on elegance and generality. It provides a _unified interface_ for neural
+operators (such as DeepONet or FNO) to be used in a plug and play fashion. As
+operator learning is particularly useful in scientific machine learning,
+**continuiti** also includes physics-informed loss functions and a collection of
+relevant benchmarks.
 
 ## Installation
 Clone the repository and install the package using pip.

docs/index.md

@@ -12,11 +12,12 @@ title: Home
 
 </div>
 
-
-**continuiti** is a Python package for machine learning on function operators.
-It implements various neural operator architectures (e.g., DeepONets),
-physics-informed loss functions to train based on PDEs, and a collection of
-examples and benchmarks.
+**continuiti** is a Python package for deep learning on function operators with
+a focus on elegance and generality. It provides a _unified interface_ for neural
+operators (such as DeepONet or FNO) to be used in a plug and play fashion. As
+operator learning is particularly useful in scientific machine learning,
+**continuiti** also includes physics-informed loss functions and a collection of
+relevant benchmarks.
 
 ::cards:: cols=2