Generative models for discovering sparse distributed representations
Authors:
- 29 August 1997
- journal article
- Published by The Royal Society in Philosophical Transactions of the Royal Society B: Biological Sciences
- Vol. 352 (1358) , 1177-1190
Abstract
Numerous specimens of the majid spider crab, Encephaloides armstrongi, were sampled from six stations (populations) between 150 and 650 m depth, on the continental slope off the coast of Oman. This extended the known geographic and bathymetric range of E. armstrongi, which is now known to occur along the continental margins of the northern Indian Ocean from the western coast of Burma to the coast of Oman. This band–like distribution is contiguous to the oxygen minimum zone in this region.Keywords
This publication has 17 references indexed in Scilit:
- The "Wake-Sleep" Algorithm for Unsupervised Neural NetworksScience, 1995
- Adaptive Rejection Sampling for Gibbs SamplingJournal of the Royal Statistical Society Series C: Applied Statistics, 1992
- Self-organizing neural network that discovers surfaces in random-dot stereogramsNature, 1992
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991
- Unsupervised LearningNeural Computation, 1989
- An analogue approach to the travelling salesman problem using an elastic net methodNature, 1987
- Non-Uniform Random Variate Generation1986
- An Introduction to Latent Variable Models1984
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982
- Understanding image intensitiesArtificial Intelligence, 1977