Skip to content

ConceptNeuronLogicality

DavidFreely edited this page Nov 11, 2025 · 6 revisions

Related: ConceptMemoryMechanisms, ConceptNeuron

It’s worth considering a special case where neuron values and synapse weights are restricted to represent digital circuits, to either 1 or 0 (fixed-weight synapses). With a synapse weight of 1, any individual neuron will cause its synapse target neurons to spike and, conversely, a neuron will fire if any incoming spike is received.

Even with a model with synapses restricted to one of two values is sufficient to represent any digital circuit. Appropriate selection of synapses can create networks that implement any basic logic component.

For energy efficiency: ConceptNeuronLogicalityEnergyEfficiency

Logicalities

!00048.jpeg

OR

Structure: A neuron with multiple incoming synapses.

Setup:

Gate: It will spike if any incoming signal value is enough to create a spike.

AND

Structure: A neuron with multiple incoming synapses.

Setup:

Gate: It will spike only if specific incoming signals together are enough to create a spike.

XOR

Structure:

Setup:

Gate:

NAND

Structure:

Setup:

Gate:

Clone this wiki locally