cnn-efficiency-from-inductive-biases

IN derived (depth 1)

Created 2026-06-21T09:59:01+00:00 · Reviewed 2026-06-21T15:37:01+00:00

CNNs achieve dramatic parameter efficiency through two complementary inductive biases — local connectivity restricts each neuron's receptive field, and weight sharing forces all spatial positions to use identical filters — reducing parameters by orders of magnitude.

Justifications

SL — Local connectivity and weight sharing jointly produce orders-of-magnitude parameter reduction

Antecedents (all must be IN):

  • IN cnn-local-connectivity — Convolutional layers differ from fully connected layers by connecting each neuron to only a local subset of neurons in the previous layer rather than all neurons
  • IN cnn-parameter-sharing-translation-invariance — Parameter sharing in convolutional layers (all neurons in a depth slice share weights and bias) reduces free parameters and provides translation invariance
  • IN cnn-weight-sharing-parameter-reduction — CNN weight sharing reduces parameters dramatically: a 5x5 kernel uses 25 weights vs 10,000 for a fully connected layer on 100x100 input

Dependents

These beliefs depend on this one: