Architectures · intermediate · concept 82 of 311 · Updated Nov 4, 2026
Convolutional Neural Network (CNN)
Architecture designed for grid-like data (images). Uses learned filters (kernels) to detect features at different scales, edges → textures → objects. Revolutionized computer vision.
Top AI contributors on this
- Geoffrey HintonUniversity of Toronto (emeritus)
- Yoshua BengioLawZero / Université de Montréal
- Yann LeCunAMI Labs / NYU
- Andrew NgDeepLearning.AI / AI Fund
- Ilya SutskeverSafe Superintelligence Inc. (SSI)
- Fei-Fei LiWorld Labs / Stanford University
Key terms
ConvolutionKernelPoolingFeature mapStride
Learn these first
Videos
▶ Neural Networks Part 8: Image Classification with Convolutional Neural Networks (CNNs) ↗
StatQuest with Josh Starmer · YouTube
▶ But what is a convolution? ↗
3Blue1Brown · YouTube
Guides and articles
Courses, papers, and more
This unlocks