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

Unlock this course with a free trial

Join today to access over 22,600 courses taught by industry experts.

Training neural networks

Training neural networks - Python Tutorial

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

Start my 1-month free trial Buy for my team

Training neural networks

“

- [Instructor] Alright I know you are probably itching to dive into some code by now, but there's a little more theory we need to cover with deep learning. I want to talk a little bit about exactly how they are trained, and some tips for tuning them now that you've had a little bit of hands on experience with them using the TensorFlow playground. How do you train a multi-layer perceptron? Well, it's using a technique called backpropagation. It's not that complicated really at a conceptual level, all we're doing is gradient descent like we talked about before using that mathematical trick of reverse-mode autodiff to make it happen efficiently. For each training step we just compute the output error for the weights that we have currently in place for each connection between each artificial neuron and then this is where backpropagation happens. Since there are multiple layers to deal with we have to take that error that's computed at the end of our neural network and back-propagate it…

Contents