liveBook · Manning

Convolution kernel

Also called convolutional filter, convolution filter, convolutional kernel

A convolution kernel is an array or tensor of weights applied to local regions of structured input to compute convolution responses.

How 11 Manning books explain it

Natural Language Processing in Action, Second Edition

A convolutional kernel is a parameter matrix or tensor whose sliding weighted operation detects a local pattern in an input sequence.

How it is used
Uses kernels to extract local word-sequence features for CNN text classification and to detect patterns in audio.
How deep it goes
Explains sliding weighted sums, multichannel tensor shapes, output lengths and learned weights through Python and PyTorch implementations.
Examples
Works through adverb moving averages, part-of-speech patterns, Morse dot detection and disaster-tweet classification.
What you can do after
Apply it via PyTorch Conv1d to match multichannel word patterns and configure kernels for text classification.

Read how Natural Language Processing in Action, Second Edition explains convolution kernel →

Math and Architectures of Deep Learning

A learned kernel applied in a convolution layer to detect local spatial patterns in images.

How it is used
Captures local patterns in arrays, images, and video by weighting neighboring values during convolution.
How deep it goes
Derives sliding weighted sums and output sizing, then relates convolution to matrix multiplication and backpropagation.
Examples
Uses moving-average curves, edge-detection signals, noisy text images, image boundaries, and a moving-ball video.
What you can do after
Apply it via PyTorch Conv1d, Conv2d, and Conv3d by setting kernel weights and tensor shapes for demonstrations.

Read how Math and Architectures of Deep Learning explains convolution kernel →

Inside Deep Learning: Math, Algorithms, Models

A learned array of weights applied over local input regions to compute convolution outputs.

How it is used
Uses kernels to highlight local image patterns and supply the spatial operation in convolutional neural networks.
How deep it goes
Works through sliding multiplication in 1D and 2D, then maps channel-spanning filters and multiple outputs to nn.Conv2d.
Examples
Uses sliding 1D and 2D filters, blur and edge detection on MNIST digits, and a two-filter PyTorch convolution.
What you can do after
Build it from scratch with sliding loops, or apply it via scipy.signal.convolve and PyTorch nn.Conv2d.

Read how Inside Deep Learning: Math, Algorithms, Models explains convolution kernel →

Deep Learning with PyTorch, Second Edition

A small learned filter window applied over local regions of an input to compute weighted sums.

How it is used
Uses kernels to detect local image patterns with weights shared across positions.
How deep it goes
Works through weighted sums, channel dimensions, learned weights, and PyTorch layer shapes, while leaving continuous convolution aside.
Examples
Uses a birds-versus-airplanes image task and handcrafted blur and vertical-edge filters.
What you can do after
Apply it via PyTorch to configure convolution layers and experiment with filter weights.

Read how Deep Learning with PyTorch, Second Edition explains convolution kernel →

Grokking AI Algorithms, Second Edition

A convolutional filter is a small learned grid of weights that detects a particular local pattern in image data.

How it is used
Uses learned filters to extract image features in a U-Net encoder and reconstruct detail in its decoder.
How deep it goes
Explains scanning and dot products with a numerical example, then illustrates padding, biases, and filter implementation.
Examples
Illustrates a row dot product and eight 3×3 filters scanning an 8×8 noisy image.
What you can do after
Evaluate/understand how learned weights produce feature maps and support image upsampling.

Read how Grokking AI Algorithms, Second Edition explains convolution kernel →

Deep Learning with Python, Third Edition

The learned weight tensor used by a convolution to transform local input patches.

How it is used
Uses filters to extract local image features and interpret what convolutional networks learn.
How deep it goes
Explains patch transformations and response maps, then works through activation maximization for inspecting learned filters.
Examples
Uses MNIST digit feature maps and synthesized patterns for filters in a pretrained Xception model.
What you can do after
Apply filter visualization via Keras and Xception to inspect patterns that activate a chosen filter.

Read how Deep Learning with Python, Third Edition explains convolution kernel →

Deep Learning with R, Third Edition

A convolution kernel is a learned weight matrix that transforms each extracted input patch into an output feature vector.

How it is used
Explains how convolutional layers extract local visual patterns and build feature maps for image classification.
How deep it goes
Explains patches, channels, response maps, padding, and strides, but stops short of formal weight calculations.
Examples
Uses MNIST dimensions, 3 × 3 and 5 × 5 windows, and channel visualizations of a cat image.
What you can do after
Evaluate learned patterns by inspecting convolutional activations and their spatial response maps.

Read how Deep Learning with R, Third Edition explains convolution kernel →

Graph Neural Networks in Action

A learnable weighted operation that transforms input data to emphasize particular patterns or features.

How it is used
Uses learned filters to extract localized patterns for image tasks and graph-based node prediction.
How deep it goes
Explains the layer pipeline and spatial-versus-spectral distinction without deriving the convolution operator mathematically.
Examples
Uses an animal image, a pixel grid, graph nodes, and graph signals to contrast convolution settings.
What you can do after
Understand how learned filters transform grid or graph data into task-relevant representations.

Read how Graph Neural Networks in Action explains convolution kernel →

Learn Generative AI with PyTorch

A learned convolutional kernel whose weights slide across local input regions to produce feature responses.

How it is used
Uses learned kernels for spatial feature extraction in convolutional neural networks, especially image classification and generation.
How deep it goes
Explains sliding multiplication, shared weights, tensor shapes, layer arguments, parameter replacement, and numerical output, but not kernel training dynamics.
Examples
Demonstrates a 2 × 2 kernel scanning a 3 × 3 grayscale tensor and producing a 2 × 2 output.
What you can do after
Build it from scratch in PyTorch by defining Conv2d arguments, assigning kernel weights, and checking the resulting feature map.

Read how Learn Generative AI with PyTorch explains convolution kernel →

Sutskever's List

A convolutional kernel is a grid of learned weights applied across local regions of an input to produce spatial responses.

How it is used
Uses learned local patterns to extract increasingly complex visual features in AlexNet’s convolutional layers.
How deep it goes
Explains sliding dot-product comparisons, feature maps, and shared weights, but does not detail how the weights are learned.
Examples
Illustrates edge and cat-part responses, plus AlexNet’s progression from 11 × 11 to 3 × 3 filters.
What you can do after
Understand how shared filters produce spatial feature maps and support hierarchical visual patterns.

Read how Sutskever's List explains convolution kernel →

Evolutionary Deep Learning: Genetic algorithms and neural networks

A convolutional filter is a learned array of weights that is slid across local input regions to produce feature responses.

How it is used
Uses learned local filters to extract image features within convolutional neural networks.
How deep it goes
Explains sliding, stride, learned weights, channel changes, and pooling, but avoids mathematical derivation.
Examples
Demonstrates Fashion-MNIST image patches, a visual filter operation, and a three-layer Keras Conv2D stack.
What you can do after
Build convolutional image layers with Keras Conv2D and inspect their output shapes and parameter counts.

Read how Evolutionary Deep Learning: Genetic algorithms and neural networks explains convolution kernel →

Also covered in

What to know first

Related concepts

Questions about convolution kernel

What is convolution kernel?

A convolution kernel is an array or tensor of weights applied to local regions of structured input to compute convolution responses.

Which Manning books explain convolution kernel?

Natural Language Processing in Action, Second Edition, Math and Architectures of Deep Learning, Inside Deep Learning: Math, Algorithms, Models, Deep Learning with PyTorch, Second Edition, Grokking AI Algorithms, Second Edition, Deep Learning with Python, Third Edition, Deep Learning with R, Third Edition, Graph Neural Networks in Action and 3 more.

What should I know before learning convolution kernel?

Manning books that teach convolution kernel usually introduce language model, backpropagation, computer vision and input first.

What is convolution kernel also called?

Convolution kernel is also called convolutional filter, convolution filter or convolutional kernel.

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.