S
Steven J. Nowlan
Researcher at Salk Institute for Biological Studies
Publications - 21
Citations - 3507
Steven J. Nowlan is an academic researcher from Salk Institute for Biological Studies. The author has contributed to research in topics: Artificial neural network & Acromegaly. The author has an hindex of 16, co-authored 21 publications receiving 3397 citations. Previous affiliations of Steven J. Nowlan include Howard Hughes Medical Institute & University of California, San Diego.
Papers
More filters
Journal Article
How Learning Can Guide Evolution.
TL;DR: The assumption that acquired character istics are not in- herited is ofte n taken to imply that adaptations t he adaptations an organism learns dur ing its lifeti me cannot guide the course of evolut ion as discussed by the authors.
Journal ArticleDOI
Simplifying neural networks by soft weight-sharing
TL;DR: A more complicated penalty term is proposed in which the distribution of weight values is modeled as a mixture of multiple gaussians, which allows the parameters of the mixture model to adapt at the same time as the network learns.
Book
How learning can guide evolution
TL;DR: The assumption that acquired character istics are not in- herited is ofte n taken to imply that adaptations t he adaptations an organism learns dur ing its lifeti me cannot guide the course of evolut ion.
Experiments on Learning by Back Propagation.
TL;DR: The learning procedure can discover appropriate weights in their kind of network, as well as determine an optimal schedule for varying the nonlinearity of the units during a search.
Patent
Handwriting recognition system and method
TL;DR: The authors proposed a system for recognizing handwritten characters, including preprocessing apparatus for generating a set of features for each handwritten character, a neural network disposed for operating on sparse data structures of those features, and post-processing for adjusting those confidence values and for selecting a character symbol consistent with external knowledge about handwritten characters and the language they are written in.