Glossary term
Glossary term
Architecture
The following two-step mathematical operation:
Element-wise multiplication of the convolutional filter and a slice of an input matrix. (The slice of the input matrix has the same rank and size as the convolutional filter.)
Summation of all the values in the resulting product matrix.
For example, consider the following 5x5 input matrix:
Now imagine the following 2x2 convolutional filter:
Each convolutional operation involves a single 2x2 slice of the input matrix. For example, suppose we use the 2x2 slice at the top-left of the input matrix. So, the convolution operation on this slice looks as follows:
A convolutional layer consists of a series of convolutional operations, each acting on a different slice of the input matrix.
For example, consider the following 5x5 input matrix:
Now imagine the following 2x2 convolutional filter:
Each convolutional operation involves a single 2x2 slice of the input matrix. For example, suppose we use the 2x2 slice at the top-left of the input matrix. So, the convolution operation on this slice looks as follows:
Created for this library
A computer vision team profiles convolutional operations on its target accelerator to choose kernel sizes that maximize throughput.
An edge AI team replaces standard convolutional operations with depthwise separable variants to reduce parameters in its on-device model.
A satellite imagery startup tunes the stride of convolutional operations to control receptive field size when detecting small objects from orbit.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License