Convolution - AshokBhat/ml GitHub Wiki

Description

• The term convolution refers to the mathematical combination of two functions to produce a third function. It merges two sets of information.
• In the case of a CNN, the convolution is performed on the input data with the use of a filter to then produce a feature map

Implementation methods

• Direct convolution - No usage of GEMMs or FFTs
• Indirect convolution - Using GEMM (via im2col), Winograd or FFT.

FAQ

• What is convolution?
• Why is it used in machine learning?

See also

• Image classification
• [CNN]] ](/AshokBhat/ml/wiki/[Convolutional-Layer) | [1x1 Convolution]]
• [GEMM]] ](/AshokBhat/ml/wiki/[[Winograd) | FFT