Update image

Author: curiousily

manuscript/04.first-neural-network.md

@@ -187,7 +187,7 @@ net = Net(X_train.shape[1])
 ann_viz(net, view=False)
 ```
 
-![svg](images/pytorch-03/04.first-neural-network_27_0.svg)
+![svg](images/pytorch-03/04.first-neural-network_27_0.png)
 
 We start by creating the layers of our model in the constructor. The `forward()` method is where the magic happens. It accepts the input `x` and allows it to flow through each layer.