Update README.md

README.md

@@ -58,7 +58,8 @@ This work is funded by [Code for Earth 2023](https://codeforearth.ecmwf.int/) in
   - [Results](#results)
 - [Technical Specifications](#technical-specifications-optional)
   - [Model Architecture and Objective](#model-architecture-and-objective)
-  - [Compute Infrastructure](#compute-infrastructure)
+  - [Loss function](#loss-function)
+  - [Computing Infrastructure](#computing-infrastructure)
     - [Hardware](#hardware)
     - [Software](#software)
 - [Authors](#authors)
@@ -246,7 +247,7 @@ accuracy across different resolutions and representations:
 By combining these loss terms, the Swin2 transformer is trained to produce accurate predictions across different resolutions and under various data transformations, 
 ensuring its versatility and robustness in diverse scenarios.
 
-## Technical Infrastructure
+## Computing Infrastructure
 
 Leveraging GPUs in deep learning initiatives greatly amplifies the pace of model training and inference. This computational edge not only diminishes the total 
 computational duration but also equips us to proficiently navigate complex tasks and extensive datasets.