Training multilevel networks to detect arbitrary Boolean functions from input/output pairs has been a long standing problem. Considerable progress has been made, but current connectionistic learning algorithms (e.g., Hinton et al., 1984; Ackley et al., 1985; Barto, 1985; Rumelhart et al., 1986) are of limited physiological relevance, and empirically are quite slow. The approaches developed here are somewhat more physiologically plausible and considerably faster.
KeywordsBoolean Function Shared Memory Back Propagation Output Node Input Pattern
Unable to display preview. Download preview PDF.