So by now we’ve learned how to build a deep neural network and how to train it to fit our data. Sometimes however, we go out there and train on ourselves and find out that nothing works as planned. Why? Because there are many things that can fail. Our architecture can be poorly chosen, our data can be noisy, our model could maybe be taking years to run and we need it to run faster. We need to learn ways to optimize the training of our models and this is what we’ll do next.