Call()
call() is the Keras method that defines the forward computation a layer or model performs on its inputs.
Deep Learning with R, Third Edition
A call method defines the forward computation performed when a neural-network layer or model receives inputs.
- How it is used
- Defines the forward data transformation executed when a Keras layer or model receives inputs.
- How deep it goes
- Explains implementation through custom dense and diffusion examples, while deferring detailed build() behavior.
- Examples
- Uses SimpleDense, shape inference, diffusion denoising, and PyTorch linear models to demonstrate forward computation.
- What you can do after
- Build custom Keras layers that transform inputs and return outputs through a call() method.
Read how Deep Learning with R, Third Edition explains call() →
Deep Learning with Python, Third Edition
A Keras layer or model method that defines the forward computation applied to inputs.
- How it is used
- Defines the forward computation inside custom Keras layers and models.
- How deep it goes
- Explains implementation with matrix multiplication and activation, while deferring broader build mechanics to adjacent treatment.
- Examples
- Uses a SimpleDense layer that multiplies inputs by W, adds b, applies ReLU, and maps 784 features to 32 outputs.
- What you can do after
- Build it from scratch by implementing call() for a custom Keras layer’s forward computation.
Read how Deep Learning with Python, Third Edition explains call() →
What to know first
- convolutional layerA convolutional layer is a neural-network layer that applies shared learned filters to local regions of structured input to produce feature representations.
Related concepts
- loopuses · A loop is a programming-language control-flow construct that repeatedly executes a block of instructions according to an iteration rule or continuation condition.
- recursionuses · Recursion is a computational technique in which a definition or procedure refers to or invokes itself, directly or indirectly.
- generationcontrasts with · Generation is the production of an output by a computational model from supplied input or context, often using patterns learned from data.
- 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.
Questions about call()
What is call()?
call() is the Keras method that defines the forward computation a layer or model performs on its inputs.
Which Manning books explain call()?
Deep Learning with R, Third Edition and Deep Learning with Python, Third Edition.
What should I know before learning call()?
Manning books that teach call() usually introduce convolutional layer first.
What is the difference between call() and generation?
call() is the Keras method that defines the forward computation a layer or model performs on its inputs. Generation is the production of an output by a computational model from supplied input or context, often using patterns learned from data.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

