Receptive field
A receptive field is the set or region of input elements whose information can influence a particular neural-network unit, representation, or output.
Deep Learning with PyTorch, Second Edition
The region of the original input that can influence a particular output unit in a convolutional network.
- How it is used
- Explains how convolutional networks combine local features to recognize larger structures.
- How deep it goes
- Traces receptive fields backward through stacked convolutions and pooling, including the effect of boundary padding.
- Examples
- Uses a 2D convolution–pooling–convolution sequence and two stacked 3D convolutions to trace input regions.
- What you can do after
- Evaluate how much input can influence an output by tracing neighborhoods backward through example convolutional networks.
Read how Deep Learning with PyTorch, Second Edition explains receptive field →
Sutskever's List
The receptive field is the region of an input that can influence a particular neural network unit's activation.
- How it is used
- Explains how deeper AlexNet units integrate information across broader image regions.
- How deep it goes
- Defines the input region affecting a unit and qualitatively explains its expansion across AlexNet’s layers.
- Examples
- Contrasts AlexNet’s 11×11 early filters with 5×5 and 3×3 filters deeper in the network.
- What you can do after
- Understand how deeper AlexNet units can capture patterns across broader image regions.
Also covered in
- Machine Learning Algorithms in Depth
- Math and Architectures of Deep Learning
- Graph Neural Networks in Action
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.
- graph neural networkA graph neural network is a neural-network model that learns representations or predictions from graph-structured data by combining information from connected entities.
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- overfittingOverfitting is a modeling condition in which a model adapts too closely to particular data, including its noise or idiosyncrasies, and consequently generalizes poorly to new data.
Related concepts
- depthproduced by · Neural-network depth is the number of successive computational layers in a neural-network architecture.
- dilated convolutionproduced by · A dilated convolution applies a filter whose sampling positions are spaced apart, expanding the receptive field without proportionally increasing kernel size or parameters.
- poolingused by · Pooling is an operation that aggregates values or representations, often summarizing local regions or combining multiple inputs into a smaller or fixed-size representation.
- downsamplingproduced by · Downsampling is the reduction of data quantity, spatial resolution, temporal resolution, or sampling rate by retaining, selecting, or aggregating fewer representative values or observations.
- convolutional neural networkproduces · A convolutional neural network is a neural-network architecture that processes structured inputs with convolutional operations, typically using learned local filters to capture patterns.
Questions about receptive field
What is receptive field?
A receptive field is the set or region of input elements whose information can influence a particular neural-network unit, representation, or output.
Which Manning books explain receptive field?
Deep Learning with PyTorch, Second Edition and Sutskever's List.
What should I know before learning receptive field?
Manning books that teach receptive field usually introduce convolutional layer, graph neural network, language model and overfitting first.
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.

