Hands-On Deep Learning with Go

Loss function

This time, our loss function is different. We are using the mean of the squared errors that have pseudocode, which looks something like this:

mse = sum( (actual_y - predicted_y) ^ 2 ) / num_of_y

This can be trivially implemented in Gorgonia as follows:

losses, err := gorgonia.Square(gorgonia.Must(gorgonia.Sub(y, m.out)))if err != nil {    log.Fatal(err)}cost := gorgonia.Must(gorgonia.Mean(losses))