Let’s look at loss function with Keras in detail and implement it in our neural network
In our previous posts we have seen MSE (means square gradient) as a loss function, but in practice there are many more efficient loss functions available to use https://keras.io/losses/
In our code we use a loss function as this
model.compile(Adam(lr=.0001), loss="sparse_categorical_crossentropy" , ..... )There are many different types of loss function to be used in different cases for optimal output.
Its again important to understand them and these are excellent blogs to follow for the same
