Bruce Rosen, James Goodwin, Jacques Vidal
to neuron-like processing elements. "neurons"
This paper examines a class of neuron based that rely on learning systems for dynamic control adaptive range coding of sensor inputs. Sensors are assumed to provide binary coded range vectors that coarsely describe the system state. These vectors are Output input decisions generated by turn the system state, subsequently producing new affect inputs. the intervals and environment are evaluated. The neural weights as well as the ran g e b 0 u n dar i e s determining the output decisions are then altered with future Preliminary reinforcement from the promise of adapting "neural experiments show receptive learning dynamical control. The observed performance with this method exceeds that of earlier approaches.
the goal of maximizing the environment.