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.

Deep learning prerequisites

Deep learning prerequisites

there are a few algorithms you need to understand first as they are important concepts of how deep learning works. One of these pre-requisites is stochastic gradient decent or SGD. That's the same as GD we talked about when we covered matrix factorization. As I mentioned it's possible to implement matrix factorization using neural networks that SGD depends on with neural networks, and we'll cover softmax which is used at the allputive neural networks to translate their raw outputs into more useful rating classifications. The first thing we want to talk about is gradient descent, this is basically a machine learning optimization technique for trying to find the most optimal set of parameters for a given problem. So what we're plotting here is basically some sort of cost function, some measurement of the error of your learning system. This applies to machine learning in general. You're going to have some sort of function that defines how close your predicted values are to the actual…

Contents