This course shows you how to solve a variety of problems using the versatile Keras functional API. You will start with simple, multi-layer dense networks (also known as multi-layer perceptrons), and continue on to more complicated architectures. The course will cover how to build models with multiple inputs and a single output, as well as how to share weights between layers in a model. We will also cover advanced topics such as category embeddings and multiple-output networks. If you've ever wanted to train a network that does both classification and regression, then this course is for you!
The Keras Functional APIFree
In this chapter, you'll become familiar with the basics of the Keras functional API. You'll build a simple functional network using functional building blocks, fit it to data, and make predictions.Keras input and dense layers50 xpInput layers100 xpDense layers100 xpOutput layers100 xpBuild and compile a model50 xpBuild a model100 xpCompile a model100 xpVisualize a model100 xpFit and evaluate a model50 xpFit the model to the tournament basketball data100 xpEvaluate the model on a test set100 xp
Two Input Networks Using Categorical Embeddings, Shared Layers, and Merge Layers
In this chapter, you will build two-input networks that use categorical embeddings to represent high-cardinality data, shared layers to specify re-usable building blocks, and merge layers to join multiple inputs to a single output. By the end of this chapter, you will have the foundational building blocks for designing neural networks with complex data flows.Category embeddings50 xpDefine team lookup100 xpDefine team model100 xpShared layers50 xpDefining two inputs100 xpLookup both inputs in the same model100 xpMerge layers50 xpOutput layer using shared layer100 xpModel using two inputs and one output100 xpPredict from your model50 xpFit the model to the regular season training data100 xpEvaluate the model on the tournament test data100 xp
Multiple Inputs: 3 Inputs (and Beyond!)
In this chapter, you will extend your 2-input model to 3 inputs, and learn how to use Keras' summary and plot functions to understand the parameters and topology of your neural networks. By the end of the chapter, you will understand how to extend a 2-input model to 3 inputs and beyond.Three-input models50 xpMake an input layer for home vs. away100 xpMake a model and compile it100 xpFit the model and evaluate100 xpSummarizing and plotting models50 xpModel summaries100 xpPlotting models100 xpStacking models50 xpAdd the model predictions to the tournament data100 xpCreate an input layer with multiple columns100 xpFit the model100 xpEvaluate the model100 xp
In this chapter, you will build neural networks with multiple outputs, which can be used to solve regression problems with multiple targets. You will also build a model that solves a regression problem and a classification problem simultaneously.Two-output models50 xpSimple two-output model100 xpFit a model with two outputs100 xpInspect the model (I)100 xpEvaluate the model100 xpSingle model for classification and regression50 xpClassification and regression in one model100 xpCompile and fit the model100 xpInspect the model (II)100 xpEvaluate on new data with two metrics100 xpWrap-up50 xp
PrerequisitesIntroduction to Deep Learning in Python
Zachary Deane-MayerSee More
VP, Data Science at DataRobot
Zach is a Data Scientist at DataRobot and co-author of the caret R package. He's fascinated by predicting the future and spends his free time competing in predictive modeling competitions. He's currently one of top 500 data scientists on Kaggle and took 9th place in the Heritage Health Prize as part of the Analytics Inside team.