cnn-biological-origin-hubel-wiesel-1959

IN premise — entries/2026/06/21/wiki-Convolutional_neural_network-chunk-7.md

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

CNNs trace their biological inspiration to Hubel and Wiesel's 1959/1968 discovery of receptive fields in cat and monkey visual cortex, with simple and complex cell hierarchies

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.
• IN ml-brain-inspiration-multiple-systems — Several machine learning architectures have documented connections to neuroscience: CNNs trace inspiration to Hubel and Wiesel's discovery of receptive fields in visual cortex, Hopfield networks established a link between recurrent neural networks and statistical mechanics (via the spin glass model rather than directly modeling neural assembly dynamics), and TD learning models dopamine-based prediction error signals in the basal ganglia.