Home › Glossary › Neural Networks › Convolutional layer

Intermediate · Neural Networks

Convolutional layer

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. A layer in a neural network that applies convolutional filters across the input to create feature maps, commonly used in image processing.

Technical Definition

A layer in a neural network that applies convolutional filters across the input to create feature maps, commonly used in image processing.

How it works

A convolutional layer is a core component of Convolutional Neural Networks (CNNs), particularly effective for processing grid-like data such as images. It consists of multiple convolutional filters that slide across the input data. Each filter detects specific local patterns, and the collective output from these filters forms feature maps, which highlight the presence and location of these patterns in the input. This layer enables the network to learn hierarchical representations of the data.

Related Concepts

  • Convolution — A mathematical operation that applies a filter to an input matrix, used in deep learning to extract features efficiently.

Further Reading

  • Google ML Glossary