fully-connected-layer-parameter-count

IN premise — entries/2026/06/21/wiki-Neural_network_28machine_learning29-chunk-7.md

Created 2026-06-21T09:55:52+00:00

The number of learnable parameters in a single fully-connected layer is (p × q) weights + q biases, where p is the number of inputs and q is the number of outputs.