PubMed · 2807768
Connectionism and an inescapable defect.
Abstract
Linear connectionist models of neurocomputing show how input patterns may be recognized, stored, compared, and recalled for output in serial-parallel, quasi-Hebbian networks. This aids the design of hardware and software for better robotics, while offering useful insights to neuroscientists studying sensorimotor systems, but connectivity via quasi-Hebbian nodes and back-propagation layers alone cannot show us how vertebrate cerebellum, allocortex, and neocortex work.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
H Stowell. 1989. Connectionism and an inescapable defect.. https://doi.org/10.3109/00207458908987445
Cite the original work for its findings. Save a collection to share your selection of sources.