Computation by neural networks. Hinton, G. E. Nature Neuroscience, 2000. abstract bibtex Networks of neurons can perform computations that have proved very difficult to emulate in conventional computers. In trying to understand how real nervous systems achieve their remarkable computational abilities, researchers have been confronted with three major theoretical issues. How can we characterize the dynamics of neural networks with recurrent connections? How do the time-varying activities of populations of neurons represent things? How are synapse strengths adjusted to learn these representations? To gain insight into these difficult theoretical issues, it has proved necessary to study grossly idealized models that are as different from real biological neural networks as apples are from planets.
@article{Hinton2000,
abstract = {Networks of neurons can perform computations that have proved very difficult to emulate in conventional computers. In trying to understand how real nervous systems achieve their remarkable computational abilities, researchers have been confronted with three major theoretical issues. How can we characterize the dynamics of neural networks with recurrent connections? How do the time-varying activities of populations of neurons represent things? How are synapse strengths adjusted to learn these representations? To gain insight into these difficult theoretical issues, it has proved necessary to study grossly idealized models that are as different from real biological neural networks as apples are from planets.},
added-at = {2007-11-04T20:58:40.000+0100},
author = {Hinton, Geoffrey E.},
biburl = {https://www.bibsonomy.org/bibtex/2e5b3ce3351812452a16af1b3f5097ff0/tmalsburg},
interhash = {f2958512ae0db9f7d95ae18434fbe0f6},
intrahash = {e5b3ce3351812452a16af1b3f5097ff0},
journal = {Nature Neuroscience},
keywords = {-23PInternalModels},
timestamp = {2007-11-04T20:58:40.000+0100},
title = {Computation by neural networks},
volume = 3,
year = 2000
}
Downloads: 0
{"_id":"4wyyhK9QFYhj6bs6Y","bibbaseid":"hinton-computationbyneuralnetworks-2000","authorIDs":["gN5Lfqjgx8P4c7HJT"],"author_short":["Hinton, G. E."],"bibdata":{"bibtype":"article","type":"article","abstract":"Networks of neurons can perform computations that have proved very difficult to emulate in conventional computers. In trying to understand how real nervous systems achieve their remarkable computational abilities, researchers have been confronted with three major theoretical issues. How can we characterize the dynamics of neural networks with recurrent connections? How do the time-varying activities of populations of neurons represent things? How are synapse strengths adjusted to learn these representations? To gain insight into these difficult theoretical issues, it has proved necessary to study grossly idealized models that are as different from real biological neural networks as apples are from planets.","added-at":"2007-11-04T20:58:40.000+0100","author":[{"propositions":[],"lastnames":["Hinton"],"firstnames":["Geoffrey","E."],"suffixes":[]}],"biburl":"https://www.bibsonomy.org/bibtex/2e5b3ce3351812452a16af1b3f5097ff0/tmalsburg","interhash":"f2958512ae0db9f7d95ae18434fbe0f6","intrahash":"e5b3ce3351812452a16af1b3f5097ff0","journal":"Nature Neuroscience","keywords":"-23PInternalModels","timestamp":"2007-11-04T20:58:40.000+0100","title":"Computation by neural networks","volume":"3","year":"2000","bibtex":"@article{Hinton2000,\n abstract = {Networks of neurons can perform computations that have proved very difficult to emulate in conventional computers. In trying to understand how real nervous systems achieve their remarkable computational abilities, researchers have been confronted with three major theoretical issues. How can we characterize the dynamics of neural networks with recurrent connections? How do the time-varying activities of populations of neurons represent things? How are synapse strengths adjusted to learn these representations? To gain insight into these difficult theoretical issues, it has proved necessary to study grossly idealized models that are as different from real biological neural networks as apples are from planets.},\n added-at = {2007-11-04T20:58:40.000+0100},\n author = {Hinton, Geoffrey E.},\n biburl = {https://www.bibsonomy.org/bibtex/2e5b3ce3351812452a16af1b3f5097ff0/tmalsburg},\n interhash = {f2958512ae0db9f7d95ae18434fbe0f6},\n intrahash = {e5b3ce3351812452a16af1b3f5097ff0},\n journal = {Nature Neuroscience},\n keywords = {-23PInternalModels},\n timestamp = {2007-11-04T20:58:40.000+0100},\n title = {Computation by neural networks},\n volume = 3,\n year = 2000\n}\n\n","author_short":["Hinton, G. E."],"key":"Hinton2000","id":"Hinton2000","bibbaseid":"hinton-computationbyneuralnetworks-2000","role":"author","urls":{},"keyword":["-23PInternalModels"],"downloads":0},"bibtype":"article","biburl":"http://www.bibsonomy.org/bib/author/Geoffrey Hinton?items=1000","creationDate":"2020-07-24T18:21:29.646Z","downloads":0,"keywords":["-23pinternalmodels"],"search_terms":["computation","neural","networks","hinton"],"title":"Computation by neural networks","year":2000,"dataSources":["9qjpnLCP4efAcKjDr"]}