Glossary term
Glossary term
Architecture
A layer of a deep neural network in which a convolutional filter passes along an input matrix. For example, consider the following 3x3 convolutional filter:
The following animation shows a convolutional layer consisting of 9 convolutional operations involving the 5x5 input matrix. Notice that each convolutional operation works on a different 3x3 slice of the input matrix. The resulting 3x3 matrix (on the right) consists of the results of the 9 convolutional operations:
Created for this library
A semiconductor manufacturer stacks several convolutional layers in its defect detector to capture features at different spatial scales.
A medical imaging team uses convolutional layers with skip connections to detect tumors at multiple resolutions in radiology scans.
A retail analytics team uses convolutional layers in its shelf-image model to detect out-of-stock spots across hundreds of products.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License