Glossary · Phase 4 · Deep learning
Channel
In images, one layer of numbers per pixel, such as red, green or blue. A CNN layer outputs one channel per filter.
A layer usually has many filters, not one. Each filter makes its own feature map. The maps stack on top of each other like pages in a book. Each page is called a channel.
Try it now
The formula from this section, live. Compare the last two lines to see why sharing a small filter is so cheap.
Learn it properly
Convolutional networks · Pattern detectors for images. About 40 minutes.
Other terms from the same lesson
- CNN: A network that slides small pattern-detectors across an image to find edges, shapes and objects.
- feature map: The grid of scores a CNN filter produces: high where its pattern appears in the image, low elsewhere.
- kernel: In a CNN, a small grid of weights that slides over an image and scores how strongly each patch matches a pattern, such as an edge.
- max pooling: Shrinking a feature map by keeping only the biggest value in each small square, so a pattern counts wherever it shows up nearby.
- padding: Extra zeros added around an image's edge so a CNN filter can be centered on edge pixels too, and the output shrinks less.
- stride: How many pixels a CNN filter moves at each step. A stride of 2 skips every other spot and halves the output size.
- vision transformer: A transformer for images: it cuts the picture into small patches and treats each patch like a word.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.