AND-gate (in neural columns)
A pre-wired neural element within a column that fires only when multiple specific inputs are active together, used to represent and gate relationships.
As defined in Forget Network Layers—Cortical Columns Think Like Graphs
Where it comes up · 1
Most important claims · 2 of 2Search all claims for “AND-gate (in neural columns)” →
- Learning a relationship in the brain occurs by selectively strengthening a tiny subset of pre-existing near-zero-weight synapses (e.g., from the 'is-a' column to an AND-gate in the Fido column and from that gate to the 'dog' output neuron), so the physical structure is already in place and learning just activates it.Forget Network Layers—Cortical Columns Think Like Graphs
- A cortical column needs only about 100 neurons because that is enough for input/output neurons, a dozen or so AND-gates, and supporting functions, which implies most of the brain's neurons are not there for brute-force learning but are scaffolding waiting to be given meaning through experience.Forget Network Layers—Cortical Columns Think Like Graphs