Advanced Deep Learning with Keras

1. The Keras Functional API

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 layers
• Input layers
• Dense layers
• Output layers
• Build and compile a model
• Build a model
• Compile a model
• Visualize a model
• Fit and evaluate a model5
• Fit the model to the tournament basketball data
• Evaluate the model on a test set

2. 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 embeddings
• Define team lookup
• Define team model
• Shared layers
• Defining two inputs
• Lookup both inputs in the same model
• Merge layers
• Output layer using shared layer
• Model using two inputs and one output
• Predict from your model
• Fit the model to the regular season training data
• Evaluate the model on the tournament test data

3. 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 models
• Make an input layer for home vs. away
• Make a model and compile it
• Fit the model and evaluate
• Summarizing and plotting models
• Model summaries
• Plotting models
• Stacking models
• Add the model predictions to the tournament data
• Create an input layer with multiple columns
• Fit the model
• Evaluate the model

4. Multiple Outputs

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 models
• Simple two-output model
• Fit a model with two outputs
• Inspect the model (I)
• Evaluate the model
• Single model for classification and regression
• Classification and regression in one model
• Compile and fit the model
• Inspect the model (II)
• Evaluate on new data with two metrics
• Wrap-up