Showing papers in "Neural Networks in 1987"

TL;DR: A study of Steepest Descent and an analysis of why it can be slow to converge and four heuristics for achieving faster rates of convergence are proposed.

TL;DR: Data are reviewed suggesting that velocity signals recorded in the magnocellular red nucleus (RNm) are produced by central motor pattern generators rather than being shaped by continuous feedback from the periphery, leading to a model of the cerebellum as an array of adjustable pattern generators.