Update usage.md

usage.md

@@ -2,13 +2,16 @@
 
 In this visualizer you can visualize gaussian processes with different kernels on different datasets.
 
-### Dataset - Generate or upload a dataset to train on.
-If generating, enter a function and the visualizer will sample points uniformly in the domain based on the settings. If uploading, make sure to upload a csv file with two columns with x being the first column and y being the second.
+---
+### Dataset 
+Generate or upload a dataset to train on. If generating, enter a function and the visualizer will sample points uniformly in the domain based on the settings.
 
-### Model - Specify the gaussian process model
-Here you can specify the gaussian process kernel, and whether to use the prior or posterior. You can also sample new y-values on the same domain. For specifying kernels, you must use the Sci-kit Learn API - see <https://scikit-learn.org/stable/modules/gaussian_process.html#kernels-for-gaussian-processes>
+---
+### Model
+Here you can specify the gaussian process kernel, and whether to use the prior or posterior. For specifying kernels, you must use the sci-kit Learn API - see <https://scikit-learn.org/stable/modules/gaussian_process.html#kernels-for-gaussian-processes>
 
-**Kernel examples**
+---
+### Kernel examples
 * RBF()
 * RBF(length_scale=1, length_scale_bounds="fixed")
 * RBF(length_scale=100, length_scale_bounds="fixed") + WhiteKernel()