Functional API

As explained in Deep Learning with Python, Third Edition

The Keras model-building interface that expresses a model as a directed acyclic graph of layers with explicit connectivity.

The Functional API builds Keras models as graphs of layers with explicit connectivity. It fits models with multiple inputs, multiple outputs, or other nonlinear topologies. section 7.2 section 7.2.2

It starts with symbolic Input tensors, applies layers to those tensors, and finishes by constructing a Model from the chosen inputs and outputs. That makes layer connectivity directly inspectable and reusable. section 7.2.2 section 7.2.5

Common uses here include:

• Building a simple two-layer model with Input, Dense, and Model. section 7.2.2
• Combining several inputs and branching to several outputs for ticket ranking and routing. section 7.2.2
• Plotting models and reusing intermediate layer outputs. section 7.2.2 section 7.2.5

Multi-input ticket classifier

Three inputs—title, text body, and tags—are concatenated, passed through a Dense feature layer, then split into priority and department outputs. The same model is trained and evaluated with either lists or dicts of arrays. section 7.2.2 section 7.2.2

Figure 7.1 Progressive disclosure of complexity for model building

Shows the progression from simple stacks to graph-like model building. section 7.2

How Deep Learning with Python, Third Edition covers it

How deep it goes

Explains symbolic inputs, layer chaining, model construction, multi-input/output wiring, plotting, and intermediate output reuse.

Examples

Uses a two-layer stack, a customer-support ticket classifier, and reused intermediate features for a new output.

What it assumes

Assumes familiarity with Sequential and basic Keras training APIs, while introducing symbolic tensors and explicit graph wiring from zero.

What you can do after

Builds graph-structured Keras models, train them with list or dict inputs and targets, and inspect or reuse layer connectivity.

How it connects

Connects with Sequential, model subclassing, Layer, Model, compile, fit, evaluate, predict, and plot_model.

liveBookmanning.com

Read Deep Learning with Python, Third Edition on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Deep Learning with R, Third EditionThe Keras Functional API is an interface for constructing models by connecting layer operations as a directed computation graph.
• 

  liveBookmanning.com
  Evolutionary Deep Learning: Genetic algorithms and neural networksThe Keras Functional API is an interface for defining neural-network models as directed graphs of layer operations and tensors.

Compare how 3 books explain Functional API →

Related concepts

• Sequential modelalternative to · A sequential model is a neural-network model comprising a linear, ordered stack of layers through which data flows from input to output.
• deep learningused by · Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
• model subclassingalternative to · Model subclassing is a technique for defining a neural-network model by creating a class that extends a model base class and specifies its computation.
• directed acyclic graphuses · A directed acyclic graph is a graph with directed edges and no directed cycles.
• graphuses · A graph is a mathematical structure consisting of vertices connected by edges that represent relationships or connections.

This explainer was generated by Manning's knowledge graph from the text of Deep Learning with Python, Third Edition. The section links point to the parts of the book it draws on.