CNN (Convolutional Neural Network)
A network that slides small filters across an image to find local patterns — the architecture that made computer vision work.
Reviewed July 10, 2026Stable
When not to use it
- On non-spatial data. The locality prior is the point; applying it to tabular columns, where neighbouring columns mean nothing, is just an odd dense network.
- At very large data scale, where the prior becomes a ceiling. Given enough images, a vision transformer can learn better structure than you assumed.
- When you need global relationships from the first layer. CNNs build receptive field gradually; some tasks want everything attending to everything immediately.
Reach for something else instead
- Vision transformers at large scale or when you need global context early — and only if you have the data.
- Classical computer vision — thresholding, template matching, edge detection — which is still unbeaten in controlled conditions like a fixed factory line.
- A pretrained model via API if the task is common. Most teams don't need to train anything.
Read more on the blog
- Who invented deep learning, and why it took so longBackpropagation was invented at least four times before it stuck. The ideas behind deep learning were mostly in place by 1990. What was missing was not insight.
- What is deep learning? The complete guideAlmost every AI system that impresses today, from chatbots to image generators to voice assistants, runs on deep learning. Its core idea is a single powerful shift: instead of humans hand-crafting the features a model uses, deep networks learn their own layered representations of data, from simple edges to whole objects. This guide explains what deep learning is, how it works, its architectures, and its limits.
- What is computer vision? How machines learn to seeYou unlock your phone with your face, a car reads the road, a scan flags a tumor: all computer vision, the branch of AI that gives machines sight. But capturing pixels is the easy part. Turning a grid of raw numbers into an understanding of what is actually in the picture is the hard problem, and this guide explains how machines learned to do it.
- How neural networks work: the idea under all of itUnder every transformer, every image generator, every language model, sits one idea: the neural network. Here's how it actually works, neurons, weights, layers, and the simple trick by which it learns from its own mistakes, explained so it finally makes sense.
A CNN slides filters over an image, building up features.
A convolution slides small filters across the image, each detecting a pattern — edges, then textures, then shapes — while pooling shrinks the map and keeps the strongest signals. Early layers see edges; deep layers see whole objects. The final layers flatten this into a classification.
Further reading
- LeCun et al. (1998), Gradient-Based Learning Applied to Document Recognition — LeNet, and the origin of the whole approach.
- Krizhevsky, Sutskever & Hinton (2012), ImageNet Classification with Deep Convolutional Neural Networks — AlexNet, the result that started the deep learning era.
- Liu et al. (2022), A ConvNet for the 2020s — CNNs rebuilt with transformer-era training recipes, and the argument that much of the gap was methodology.
Primary sources, listed so you can check the claims on this page rather than take them on trust.
Where people go wrong
- Training from scratch on a few thousand images. Fine-tuning a pretrained model will beat it, in less time, almost always.
- Skipping augmentation, then adding layers to fix the resulting overfitting. Augmentation is the cheaper fix and usually the better one.
- Validating on data that resembles training data more than reality does. The model looks excellent right up until it meets a real camera.
At a glance
FieldDeep Learning
Core ideaslide learned filters over local patches
Key propertiesparameter sharing, locality
Priortranslation equivariance
Best defaultfine-tune a pretrained ResNet
DifficultyIntermediate
Often compared with
CNN vs. vision transformer — a built-in assumption about images vs. learning that structure from far more data.
Where this sits
4 concepts come first. Understanding it opens up 18 more.
4Levelsteps in
4Needs firstconcepts
18Opens up6% of 310
3Areascrosses fields
Learn these firstNeural Network
Computed from the prerequisite graph, not assigned. How this works