The Nature of Statistical Learning Theory View Full Text


Ontology type: schema:Book      Open Access: True


Book Info

DATE

1995

GENRE

Monograph

AUTHORS

Vladimir N. Vapnik

PUBLISHER

Springer Nature

ABSTRACT

The aim of this book is to discuss the fundamental ideas which lie behind the statistical theory of learning and generalization. It considers learning from the general point of view of function estimation based on empirical data. Omitting proofs and technical details, the author concentrates on discussing the main results of learning theory and their connections to fundamental problems in statistics. These include: - the general setting of learning problems and the general model of minimizing the risk functional from empirical data - a comprehensive analysis of the empirical risk minimization principle and shows how this allows for the construction of necessary and sufficient conditions for consistency - non-asymptotic bounds for the risk achieved using the empirical risk minimization principle - principles for controlling the generalization ability of learning machines using small sample sizes - introducing a new type of universal learning machine that controls the generalization ability. More... »

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-1-4757-2440-0

DOI

http://dx.doi.org/10.1007/978-1-4757-2440-0

ISBN

978-1-4757-2442-4 | 978-1-4757-2440-0

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1027312764


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "AT&T Bell Laboratories, 101 Crawfords Corner Road, 07733, Holmdel, NJ, USA", 
          "id": "http://www.grid.ac/institutes/grid.469490.6", 
          "name": [
            "AT&T Bell Laboratories, 101 Crawfords Corner Road, 07733, Holmdel, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Vapnik", 
        "givenName": "Vladimir N.", 
        "id": "sg:person.012166363434.68", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012166363434.68"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "1995", 
    "datePublishedReg": "1995-01-01", 
    "description": "The aim of this book is to discuss the fundamental ideas which lie behind the statistical theory of learning and generalization. It considers learning from the general point of view of function estimation based on empirical data. Omitting proofs and technical details, the author concentrates on discussing the main results of learning theory and their connections to fundamental problems in statistics. These include: - the general setting of learning problems and the general model of minimizing the risk functional from empirical data - a comprehensive analysis of the empirical risk minimization principle and shows how this allows for the construction of necessary and sufficient conditions for consistency - non-asymptotic bounds for the risk achieved using the empirical risk minimization principle - principles for controlling the generalization ability of learning machines using small sample sizes - introducing a new type of universal learning machine that controls the generalization ability.", 
    "genre": "monograph", 
    "id": "sg:pub.10.1007/978-1-4757-2440-0", 
    "isAccessibleForFree": true, 
    "isbn": [
      "978-1-4757-2442-4", 
      "978-1-4757-2440-0"
    ], 
    "keywords": [
      "universal learning machines", 
      "statistical learning theory", 
      "empirical risk minimization", 
      "empirical risk minimization principle", 
      "statistical theory", 
      "asymptotic bounds", 
      "risk minimization principle", 
      "sufficient conditions", 
      "general setting", 
      "function estimation", 
      "minimization principle", 
      "risk minimization", 
      "generalization ability", 
      "fundamental idea", 
      "fundamental problem", 
      "general model", 
      "theory", 
      "main results", 
      "general point", 
      "problem", 
      "bounds", 
      "learning machine", 
      "small samples", 
      "empirical data", 
      "generalization", 
      "minimization", 
      "learning theory", 
      "statistics", 
      "estimation", 
      "technical details", 
      "proof", 
      "new type", 
      "machine", 
      "model", 
      "principles", 
      "point", 
      "connection", 
      "detail", 
      "idea", 
      "construction", 
      "comprehensive analysis", 
      "data", 
      "conditions", 
      "results", 
      "nature", 
      "analysis", 
      "types", 
      "authors", 
      "view", 
      "learning", 
      "book", 
      "ability", 
      "setting", 
      "samples", 
      "aim", 
      "risk"
    ], 
    "name": "The Nature of Statistical Learning Theory", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1027312764"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-1-4757-2440-0"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-1-4757-2440-0", 
      "https://app.dimensions.ai/details/publication/pub.1027312764"
    ], 
    "sdDataset": "books", 
    "sdDatePublished": "2022-08-04T17:13", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220804/entities/gbq_results/book/book_16.jsonl", 
    "type": "Book", 
    "url": "https://doi.org/10.1007/978-1-4757-2440-0"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-1-4757-2440-0'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-1-4757-2440-0'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-1-4757-2440-0'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-1-4757-2440-0'


 

This table displays all metadata directly associated to this object as RDF triples.

105 TRIPLES      20 PREDICATES      80 URIs      73 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-1-4757-2440-0 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 schema:author N255fb9f643864e54b6ff4c24804a9b97
4 schema:datePublished 1995
5 schema:datePublishedReg 1995-01-01
6 schema:description The aim of this book is to discuss the fundamental ideas which lie behind the statistical theory of learning and generalization. It considers learning from the general point of view of function estimation based on empirical data. Omitting proofs and technical details, the author concentrates on discussing the main results of learning theory and their connections to fundamental problems in statistics. These include: - the general setting of learning problems and the general model of minimizing the risk functional from empirical data - a comprehensive analysis of the empirical risk minimization principle and shows how this allows for the construction of necessary and sufficient conditions for consistency - non-asymptotic bounds for the risk achieved using the empirical risk minimization principle - principles for controlling the generalization ability of learning machines using small sample sizes - introducing a new type of universal learning machine that controls the generalization ability.
7 schema:genre monograph
8 schema:isAccessibleForFree true
9 schema:isbn 978-1-4757-2440-0
10 978-1-4757-2442-4
11 schema:keywords ability
12 aim
13 analysis
14 asymptotic bounds
15 authors
16 book
17 bounds
18 comprehensive analysis
19 conditions
20 connection
21 construction
22 data
23 detail
24 empirical data
25 empirical risk minimization
26 empirical risk minimization principle
27 estimation
28 function estimation
29 fundamental idea
30 fundamental problem
31 general model
32 general point
33 general setting
34 generalization
35 generalization ability
36 idea
37 learning
38 learning machine
39 learning theory
40 machine
41 main results
42 minimization
43 minimization principle
44 model
45 nature
46 new type
47 point
48 principles
49 problem
50 proof
51 results
52 risk
53 risk minimization
54 risk minimization principle
55 samples
56 setting
57 small samples
58 statistical learning theory
59 statistical theory
60 statistics
61 sufficient conditions
62 technical details
63 theory
64 types
65 universal learning machines
66 view
67 schema:name The Nature of Statistical Learning Theory
68 schema:productId N035e23882b0a401987c6f8a3363f82f9
69 N89f787e3fd90440d82f3297ffafa4396
70 schema:publisher N928895bdd813499c88ce2b8f9c9f1cf0
71 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027312764
72 https://doi.org/10.1007/978-1-4757-2440-0
73 schema:sdDatePublished 2022-08-04T17:13
74 schema:sdLicense https://scigraph.springernature.com/explorer/license/
75 schema:sdPublisher N431f737f52c74cd8a01ecf7b3ee1c833
76 schema:url https://doi.org/10.1007/978-1-4757-2440-0
77 sgo:license sg:explorer/license/
78 sgo:sdDataset books
79 rdf:type schema:Book
80 N035e23882b0a401987c6f8a3363f82f9 schema:name dimensions_id
81 schema:value pub.1027312764
82 rdf:type schema:PropertyValue
83 N255fb9f643864e54b6ff4c24804a9b97 rdf:first sg:person.012166363434.68
84 rdf:rest rdf:nil
85 N431f737f52c74cd8a01ecf7b3ee1c833 schema:name Springer Nature - SN SciGraph project
86 rdf:type schema:Organization
87 N89f787e3fd90440d82f3297ffafa4396 schema:name doi
88 schema:value 10.1007/978-1-4757-2440-0
89 rdf:type schema:PropertyValue
90 N928895bdd813499c88ce2b8f9c9f1cf0 schema:name Springer Nature
91 rdf:type schema:Organisation
92 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
93 schema:name Mathematical Sciences
94 rdf:type schema:DefinedTerm
95 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
96 schema:name Statistics
97 rdf:type schema:DefinedTerm
98 sg:person.012166363434.68 schema:affiliation grid-institutes:grid.469490.6
99 schema:familyName Vapnik
100 schema:givenName Vladimir N.
101 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012166363434.68
102 rdf:type schema:Person
103 grid-institutes:grid.469490.6 schema:alternateName AT&T Bell Laboratories, 101 Crawfords Corner Road, 07733, Holmdel, NJ, USA
104 schema:name AT&T Bell Laboratories, 101 Crawfords Corner Road, 07733, Holmdel, NJ, USA
105 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...