Intermediate · Neural Networks
Convolutional operation
Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.
TL;DR. The core calculation where a convolutional filter's values are element-wise multiplied with a slice of the input matrix, and the results are summed.
Technical Definition
The core calculation where a convolutional filter's values are element-wise multiplied with a slice of the input matrix, and the results are summed.
How it works
A convolutional operation is the fundamental mathematical process performed by a convolutional filter on a portion of the input data. It involves taking a small section (slice) of the input matrix that matches the size of the filter, performing element-wise multiplication between the filter's weights and the input slice, and then summing up all the resulting products. This single sum produces one value in the output feature map, representing the detection of a specific feature in that input region.
Related Concepts
- Convolution — A mathematical operation that applies a filter to an input matrix, used in deep learning to extract features efficiently.
- Convolutional filter — A small matrix used in convolutional operations to detect specific features like edges or textures within an input matrix.