How deeply does Deep Learning with Python, Third Edition cover call()?

Explains implementation with matrix multiplication and activation, while deferring broader build mechanics to adjacent treatment.

Call()

As explained in Deep Learning with Python, Third Edition

A Keras layer or model method that defines the forward computation applied to inputs.

In Keras, call() defines what a layer or model does during its forward pass. It receives input tensors, applies the layer’s computation, and returns output tensors. The layer is used like a function because __call__() invokes call() for you. section 3.6.2

A simple dense computation

A custom dense layer can implement call() as `y = keras.ops.matmul(inputs, self.W) + self.b`, then apply an activation when one is configured. Calling `my_dense` with a tensor shaped `(2, 784)` produces an output shaped `(2, 32)`.

Keep these roles distinct:

build() creates weight state when the input shape becomes known; call() uses that state to compute outputs. section 3.6.2

How Deep Learning with Python, Third Edition covers it

Cover of Deep Learning with Python, Third Edition

liveBook manning.com

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

Also explained in

liveBook manning.com

Deep Learning with R, Third EditionA call method defines the forward computation performed when a neural-network layer or model receives inputs.

Compare how 2 books explain call() →

Related concepts

loopuses · A loop is a programming control-flow construct that repeatedly executes a block of instructions according to an iteration rule or continuation condition.
generationcontrasts with · Generation is the computational production of outputs from supplied inputs or context, often by applying a model to produce predictions or new content.
recursionuses · Recursion is a computational technique in which a definition or procedure refers to or invokes the same definition or procedure, directly or indirectly.
build()equivalent to · build() is a Keras method that creates a layer’s or model’s state, including weights, after the input shape is known.

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.