cnn-translation-equivariant-not-invariant

IN premise — entries/2026/06/21/wiki-Convolutional_neural_network-chunk-1.md

Created 2026-06-21T09:55:49+00:00

CNNs produce translation-equivariant feature maps but are typically NOT translation-invariant due to downsampling/pooling — a common misconception

Dependents

These beliefs depend on this one:

• IN cnn-biologically-inspired-but-technically-imprecise — CNNs are biologically inspired (receptive fields from Hubel-Wiesel 1959) but technically imprecise in two ways: the "convolution" operation is actually cross-correlation, and the features are translation-equivariant rather than translation-invariant as commonly claimed.