Showing papers in "Neurocomputing in 1990"

TL;DR: Analyzing the possibility of predicting stock prices on a short-term, day-to-day basis with help of neural networks by studying three important German stocks chosen at random found that neural network could considerably improve the prognosis of stock prices in the future.

TL;DR: Pattern recognition based methodology implemented in the architecture of artificial neural network can be used to model knowledge intensive feedback control systems to develop and practical design of neural-net based control systems.

TL;DR: It is concluded that neural networks can be used for drug design and discovery and to provide information for patient care.

TL;DR: The work described below concerns speaker adaptation, noise immunity, classification of speech parameters using a set of “phonetic” symbols, investigation of relevant graphemic symbols, and classification of a sequence of feature vectors by lexical access.

TL;DR: A hybrid approach is described which combines the strengths of adaptive networks and behavioral economics to optimize the allocation of resources and the BANKET software which implements it is described.

TL;DR: Only if a new technology is unquestionably successful and clearly has been demonstrated to be an order of magnitude better than evolving traditional methods will new technologies such as neural networks be adopted.