From the course: Building Recommender Systems with Machine Learning and AI

Unlock this course with a free trial

Join today to access over 22,400 courses taught by industry experts.

Tuning neural networks

Tuning neural networks

- Let's talk about overfitting as well. You can see you'll often end up with patterns like this, where you're not really getting a clean solution. You end up with these weird spikes sometimes and sometimes if you let things go a little bit too long, it ends up reinforcing those spikes. Those overfitted areas where you're not really fitting to the pattern you're looking for, you're just fitting to the training data that you were given. Obviously if you have thousands of weights to tune, those connections between each neuron and each layer of your neurons can add up really quickly. So it's very easy for overfitting to happen, but fortunately there are ways to deal with it. One is called early stopping. So as soon as you see performance start to drop, that might be nature's way of telling you that it might be time for you to stop learning. At this point maybe you're just overfitting. There are also regularization terms you can add to the cost function during training which are like the…

Contents