Over the past few weeks, we’ve gone over gradient descent and neural networks, and you’ve learned the basics of how to write a machine learning algorithm. This week, we’re going to take it a step further -- how do we get our networks to generalize to new datasets? We’ll be tackling the tricky phenomenon of overfitting, which occurs when your model memorizes your input and fails on new examples. Come join us and learn a variety of techniques designed to reduce overfitting and increase overall accuracy of your algorithms.