5,321
edits
(Created page with "Machine Learning, Computer Vision, and Computer Graphics Glossary ==N== * Normalized Device Coordinates - In images, pixels are in coordinates of <math>[-1, 1]\times[-1, 1]...") |
No edit summary |
||
Line 1: | Line 1: | ||
Machine Learning, Computer Vision, and Computer Graphics Glossary | Machine Learning, Computer Vision, and Computer Graphics Glossary | ||
==C== | |||
* [[Convolutional neural network]] or CNN - A neural network architecture for image data, or other data on a regular grid. | |||
==D== | |||
* Dilation - how spread out a CNN kernel is. See [[Convolutional neural network]]. | |||
==F== | |||
* Fully connected network - The standard neural network model where each layer is a sequence of nodes. | |||
==G== | |||
* Graph Neural Network | |||
==I== | |||
* Intersection over Union - A metric for computing the accuracy of bounding box prediction. | |||
==M== | |||
* Multilayer perceptron - See Fully connected network. | |||
==N== | ==N== | ||
* Normalized Device Coordinates - In images, pixels are in coordinates of <math>[-1, 1]\times[-1, 1] </math>. | * Normalized Device Coordinates - In images, pixels are in coordinates of <math>[-1, 1]\times[-1, 1] </math>. | ||
==S== | |||
* Stride - how far the CNN kernel in terms of input pixels moves between output pixels. | |||
==T== | |||
* [[Transformer (machine learning model)]] - A neural network architecture for sequence data. |