liveBook · Manning

Convolutional neural network

As explained in Timeless Algorithms, The Foundational Ideas

A convolutional neural network is a neural network architecture that uses convolutional operations to learn patterns in structured data such as images.

Convolutional neural networks tailor network designs to image structure, learning increasingly complex visual patterns. This approach supports representation learning: transforming raw pixels into useful features such as edges, shapes, and objects instead of relying only on handcrafted features. section 11.1 section 11.1

Deep convolutional networks achieved a major breakthrough in the 2012 ImageNet competition, helping establish the foundations of modern computer vision. section 11.1

How Timeless Algorithms, The Foundational Ideas covers it

How deep it goes
Characterizes image-structure-aware pattern learning, but does not detail convolutional operations or network layers.
Examples
Uses image features such as edges, shapes, and objects, alongside the 2012 ImageNet breakthrough.
What you can do after
Understand how image-structured networks learn visual patterns and contribute to computer vision.
How it connects
Connects convolutional neural networks to deep learning, representation learning, and computer vision.

Also explained in

Compare how 21 books explain convolutional neural network →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Timeless Algorithms, The Foundational Ideas. The section links point to the parts of the book it draws on.