added information about the auxiliary head

README.md

@@ -12,9 +12,11 @@ metrics:
 
 # wide-and-deep-net-california-housing-v3
 
-A wide & deep neural network trained on the California Housing dataset.
+A wide & deep neural network trained on the California Housing dataset. It is a PyTorch adaptation of the TensorFlow model in Chapter 10 of Aurelien Geron's book 'Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow'.
 
-It takes eight features: `'MedInc'`, `'HouseAge'`, `'AveRooms'`, `'AveBedrms'`, `'Population'`, `'AveOccup'`, `'Latitude'` and `'Longitude'`. It predicts `'MedHouseVal'`.
+![](https://raw.githubusercontent.com/sambitmukherjee/handson-ml3-pytorch/main/chapter10/Figure_10-15.png)
+
+The model takes eight features: `'MedInc'`, `'HouseAge'`, `'AveRooms'`, `'AveBedrms'`, `'Population'`, `'AveOccup'`, `'Latitude'` and `'Longitude'`. It predicts `'MedHouseVal'`.
 
 The first five features (`'MedInc'`, `'HouseAge'`, `'AveRooms'`, `'AveBedrms'` and `'Population'`) flow through the wide path.
 
@@ -22,9 +24,7 @@ The last six features (`'AveRooms'`, `'AveBedrms'`, `'Population'`, `'AveOccup'`
 
 Note: The features `'AveRooms'`, `'AveBedrms'` and `'Population'` flow through both the wide path and the deep path.
 
-This model is a PyTorch adaptation of the TensorFlow model in Chapter 10 of Aurelien Geron's book 'Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow'.
-
-![](https://raw.githubusercontent.com/sambitmukherjee/handson-ml3-pytorch/main/chapter10/Figure_10-15.png)
+The model also has an auxiliary head. The main head and the auxiliary head output the same thing (`'MedHouseVal'`). As mentioned in the book, this is a regularization technique, to try and ensure that the "underlying part of the network" (i.e., the deep path) learns something useful on its own, without relying on the rest of the network.
 
 Code: https://github.com/sambitmukherjee/handson-ml3-pytorch/blob/main/chapter10/wide_and_deep_net_california_housing_v3.ipynb