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

Unlock this course with a free trial

Join today to access over 23,200 courses taught by industry experts.

Classifier patterns with Keras

Classifier patterns with Keras - Python Tutorial

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

Start my 1-month free trial Buy for my team

Classifier patterns with Keras

“

- [Instructor] So that was a lot easier using keras, wasn't it? The MNIST data set is just one type of problem that you might solve with a neural network. It's what we call a multi-class classification. It's multi-class because the classifications we are fitting into range from the numbers zero through nine. So in this case, we have 10 different possible classification values and that makes this a multi-class classification problem. Based on Keras' documentation and examples, they have general advice on how to handle different types of problems. Here's an example of how they suggest setting up a multi-class classification problem in general. You can see here that we have two hidden layers. We have an input dimension of however many features you have coming into this system. In this example there's 20, but depending on the nature of your problem there may be more or less. It's setting up two relu activation function layers, each with 64 neurons. Again that's something you'd want to…

Contents