Any logical expression can be implemented by a neural network

Evidence

“Because of the ‘all-or-none’ character of nervous activity,” they write, “neural events and the relations among them can be treated by means of propositional logic. It is found that the behavior of every net can be described in these terms … and that for any logical expression satisfying certain conditions, one can find a net behaving in the fashion it describes.” — Brian Christian, The Alignment Problem, 15

Categorization

• DEFINE: The founding theoretical claim of the field: the equivalence between logic and neural nets.
• corroborated: 2 independent passages support this claim — Brian Christian, The Alignment Problem, 15
• XREF: connects to: Real neurons proved far messier than the logic-gate model predicted — Brian Christian, The Alignment Problem, 16; The brain’s all-or-nothing neuron firing resembles binary logic — Brian Christian, The Alignment Problem, 12

Related

• The brain’s all-or-nothing neuron firing resembles binary logic (similarity 0.85)
• Real neurons proved far messier than the logic-gate model predicted (similarity 0.83)

Broader Connections

• The brain’s all-or-nothing neuron firing resembles binary logic #corroborates (0.55) — Brian Christian, The Alignment Problem, 12