What is a convolution?
In mathematics, casually speaking, a mixture of two functions.
convolution explained in plain English
In mathematics, casually speaking, a mixture of two functions. In machine learning, a convolution mixes the convolutional filter and the input matrix in order to train weights. The term "convolution" in machine learning is often a shorthand way of referring to either convolutional operation or convolutional layer. Without convolutions, a machine learning algorithm would have to learn a separate weight for every cell in a large tensor. For example, a machine learning algorithm training on 2K x 2K images would be forced to find 4M separate weights. Thanks to convolutions, a machine learning algorithm only has to find weights for every cell in the convolutional filter, dramatically reducing the memory needed to train the model. When the convolutional filter is applied, it is simply replicated across cells such that each is multiplied by the filter.
Example
Practitioners refer to convolution when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- convolutional filter
One of the two actors in a convolutional operation.
- convolutional layer
A layer of a deep neural network in which a convolutional filter passes along an input matrix.
- convolutional operation
The following two-step mathematical operation: 1.
- stride
In a convolutional operation or pooling, the delta in each dimension of the next series of input slices.
- autoencoder
A system that learns to extract the most important information from the input.
- auxiliary loss
A loss function—used in conjunction with a neural network model's main loss function—that helps accelerate training during the early iterations when weights are randomly initialized.
- Backpropagation
The process that tells a neural network which internal settings caused an error and how to adjust them, working backwards through layers.
- Bayesian neural network
A probabilistic neural network that accounts for uncertainty in weights and outputs.
- convex function
A function in which the region above the graph of the function is a convex set.
- convolutional neural network
A neural network in which at least one layer is a convolutional layer.