How are input neurons and output neurons used in a neural-net automaton?

In the context of automata theory, a neural-net automaton is a mathematical model of a neural net that processes information through quantized pulses of excitation. Input and output neurons serve as the interface between the automaton and its environment:1

• Input Neurons: These neurons mathematically represent physiological receptors. They are excited or left quiescent by the exterior environment, effectively receiving stimuli that the automaton then processes. At any given instant, an input neuron is either excited (represented by the binary digit 1) or nonexcited (represented by 0).123
• Output Neurons: These neurons record the logical state of the configuration after a specific time delay. They transmit the automaton's computed effect back to the exterior environment. A response is recorded as a configuration of binary digits corresponding to the states of these output neurons at a future time t.12

By interconnecting these neurons, the automaton can compute logical statements, such as those found in propositional calculus, by matching its output responses to the truth values of logical functions.4