Furkan Arslan

If the neural network is not learning enough it’s underfitting. The opposite is overfitting. That’s when it has learned too much from the training data.

Now one day you try out a different strategy — sacrificing one of your own bishops to save your queen and take the other’s rook. Bam you realize this is so amazing. You’ve added this new trick to your training set, which you would never have learned if you had kept just practicing your previous noob strategy.