Neurophysiological studies reveal a neural network in the brain stem that converts a velocity to a position signal to mediate the vestibulo reflex. This integrator is calibrated at birth and then maintained through disease and trauma. Therefore, it is a network that learns. It was modeled by a group of interconnected neurons that received a continuous time function at its input and generated a continuous output. The output was monitored to create an error. The network learned on a trial-and-error, synapse-by-synapse algorithm. The resulting network integrated by forming multiple positive feedback loops. Cell behaviour was distributed and resembled that seen with microelectrodes in the real integrator

The empirical testing of error repair schemes for skeletons of source programs in a block-structured language leads to the problem of generating balanced parenthesis strings in a uniform random manner. An efficient generator which works from left to right must compute the correct probability for the next symbol at each stage of the generation. The associated enumeration problem may be solved by adopting a geometric interpretation usually associated with random walk problems. This solution leads immediately to an O ( n ) algorithm for the generator.