@INCOLLECTION{newtonVC,
   AUTHOR       = {E.D. Sontag},
   BOOKTITLE    = {Neural Networks and Machine Learning},
   PUBLISHER    = {Springer, Berlin},
   TITLE        = {VC dimension of neural networks},
   YEAR         = {1998},
   OPTADDRESS   = {},
   OPTCHAPTER   = {},
   OPTCROSSREF  = {},
   OPTEDITION   = {},
   EDITOR       = {C.M. Bishop},
   OPTMONTH     = {},
   OPTNOTE      = {},
   OPTNUMBER    = {},
   PAGES        = {69-95},
   OPTSERIES    = {},
   OPTTYPE      = {},
   OPTVOLUME    = {},
   KEYWORDS     = {neural networks, VC dimension, learning, 
      neural networks, shattering},
   PDF          = {../../FTPDIR/vc-expo.pdf},
   ABSTRACT     = { The Vapnik-Chervonenkis (VC) dimension is an integer 
      which helps to characterize distribution-independent learning of 
      binary concepts from positive and negative samples. This paper, based 
      on lectures delivered at the Isaac Newton Institute in August of 
      1997, presents a brief introduction, establishes various elementary 
      results, and discusses how to estimate the VC dimension in several 
      examples of interest in neural network theory. (It does not address 
      the learning and estimation-theoretic applications of VC dimension, 
      and the applications to uniform convergence theorems for empirical 
      probabilities, for which many suitable references are available.) }
}

{"_id":"Gs2RoGKngcB4qZGFm","bibbaseid":"sontag-vcdimensionofneuralnetworks-1998","downloads":0,"creationDate":"2018-10-18T05:07:06.405Z","title":"VC dimension of neural networks","author_short":["Sontag, E."],"year":1998,"bibtype":"incollection","biburl":"http://www.sontaglab.org/PUBDIR/Biblio/complete-bibliography.bib","bibdata":{"bibtype":"incollection","type":"incollection","author":[{"firstnames":["E.D."],"propositions":[],"lastnames":["Sontag"],"suffixes":[]}],"booktitle":"Neural Networks and Machine Learning","publisher":"Springer, Berlin","title":"VC dimension of neural networks","year":"1998","optaddress":"","optchapter":"","optcrossref":"","optedition":"","editor":[{"firstnames":["C.M."],"propositions":[],"lastnames":["Bishop"],"suffixes":[]}],"optmonth":"","optnote":"","optnumber":"","pages":"69-95","optseries":"","opttype":"","optvolume":"","keywords":"neural networks, VC dimension, learning, neural networks, shattering","pdf":"../../FTPDIR/vc-expo.pdf","abstract":"The Vapnik-Chervonenkis (VC) dimension is an integer which helps to characterize distribution-independent learning of binary concepts from positive and negative samples. This paper, based on lectures delivered at the Isaac Newton Institute in August of 1997, presents a brief introduction, establishes various elementary results, and discusses how to estimate the VC dimension in several examples of interest in neural network theory. (It does not address the learning and estimation-theoretic applications of VC dimension, and the applications to uniform convergence theorems for empirical probabilities, for which many suitable references are available.) ","bibtex":"@INCOLLECTION{newtonVC,\n AUTHOR = {E.D. Sontag},\n BOOKTITLE = {Neural Networks and Machine Learning},\n PUBLISHER = {Springer, Berlin},\n TITLE = {VC dimension of neural networks},\n YEAR = {1998},\n OPTADDRESS = {},\n OPTCHAPTER = {},\n OPTCROSSREF = {},\n OPTEDITION = {},\n EDITOR = {C.M. Bishop},\n OPTMONTH = {},\n OPTNOTE = {},\n OPTNUMBER = {},\n PAGES = {69-95},\n OPTSERIES = {},\n OPTTYPE = {},\n OPTVOLUME = {},\n KEYWORDS = {neural networks, VC dimension, learning, \n neural networks, shattering},\n PDF = {../../FTPDIR/vc-expo.pdf},\n ABSTRACT = { The Vapnik-Chervonenkis (VC) dimension is an integer \n which helps to characterize distribution-independent learning of \n binary concepts from positive and negative samples. This paper, based \n on lectures delivered at the Isaac Newton Institute in August of \n 1997, presents a brief introduction, establishes various elementary \n results, and discusses how to estimate the VC dimension in several \n examples of interest in neural network theory. (It does not address \n the learning and estimation-theoretic applications of VC dimension, \n and the applications to uniform convergence theorems for empirical \n probabilities, for which many suitable references are available.) }\n}\n\n","author_short":["Sontag, E."],"editor_short":["Bishop, C."],"key":"newtonVC","id":"newtonVC","bibbaseid":"sontag-vcdimensionofneuralnetworks-1998","role":"author","urls":{},"keyword":["neural networks","VC dimension","learning","neural networks","shattering"],"downloads":0,"html":""},"search_terms":["dimension","neural","networks","sontag"],"keywords":["neural networks","vc dimension","learning","neural networks","shattering"],"authorIDs":[],"dataSources":["DKqZbTmd7peqE4THw"]}