Machine Learning & AI

Advanced

Discrete Convolution

Slides a filter over an input to detect local patterns; the core of CNNs.

Formula

(f*g)(t)=\sum_{\tau} f(\tau)\,g(t-\tau)

Variables

fInput signal

gKernel/filter

\tauShift index

Example

A 3x3 edge kernel highlights boundaries

Did You Know?

Convolutional nets are inspired by the visual cortex, where neurons respond to local regions.

cnn convolution vision

Share this formula

More in Machine Learning & AI

Linear Regression Model

Predicts a continuous value as a weighted sum of input features plus a bias.

Gradient Descent Update

Iteratively moves parameters in the direction that most reduces the loss.

ReLU Activation

Rectified Linear Unit: outputs the input if positive, else zero.

Leaky ReLU

A ReLU variant that lets a small gradient flow for negative inputs.

Tanh Activation

Squashes input to the range (-1, 1); zero-centred activation.

Softmax

Turns a vector of scores into a probability distribution that sums to 1.