Computational machine learning in theory and praxis View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

1995

AUTHORS

Ming Li , Paul Vitányi

ABSTRACT

In the last few decades a computational approach to machine learning has emerged based on paradigms from recursion theory and the theory of computation. Such ideas include learning in the limit, learning by enumeration, and probably approximately correct (pac) learning. These models usually are not suitable in practical situations. In contrast, statistics based inference methods have enjoyed a long and distinguished career. Currently, Bayesian reasoning in various forms, minimum message length (MML) and minimum description length (MDL), are widely applied approaches. They are the tools to use with particular machine learning praxis such as simulated annealing, genetic algorithms, genetic programming, artificial neural networks, and the like. These statistical inference methods select the hypothesis which minimizes the sum of the length of the description of the hypothesis (also called ‘model’) and the length of the description of the data relative to the hypothesis. It appears to us that the future of computational machine learning will include combinations of the approaches above coupled with guaranties with respect to used time and memory resources. Computational learning theory will move closer to practice and the application of the principles such as MDL require further justification. Here, we survey some of the actors in this dichotomy between theory and praxis, we justify MDL via the Bayesian approach, and give a comparison between pac learning and MDL learning of decision trees. More... »

PAGES

518-535

Book

TITLE

Computer Science Today

ISBN

978-3-540-60105-0
978-3-540-49435-5

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/bfb0015264

DOI

http://dx.doi.org/10.1007/bfb0015264

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1020796250


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/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Waterloo", 
          "id": "https://www.grid.ac/institutes/grid.46078.3d", 
          "name": [
            "Computer Science Department, University of Waterloo, N2L 3G1\u00a0Waterloo, Ontario, Canada"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Li", 
        "givenName": "Ming", 
        "id": "sg:person.0621576316.79", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0621576316.79"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Amsterdam", 
          "id": "https://www.grid.ac/institutes/grid.7177.6", 
          "name": [
            "CWI and University of Amsterdam, Kruislaan 413, 1098\u00a0SJ Amsterdam, The Netherlands"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Vit\u00e1nyi", 
        "givenName": "Paul", 
        "id": "sg:person.014213763741.01", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014213763741.01"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/s0019-9958(67)91165-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006283457"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0890-5401(89)90010-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017419784"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0005-1098(78)90005-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018373874"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0005-1098(78)90005-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018373874"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0022-0000(92)90026-f", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025072502"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1968.1972", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038881641"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1070/rm1970v025n06abeh001269", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1058193982"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tit.1978.1055913", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061648116"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tit.1984.1056936", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061649057"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1137/0220056", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062842316"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1995", 
    "datePublishedReg": "1995-01-01", 
    "description": "In the last few decades a computational approach to machine learning has emerged based on paradigms from recursion theory and the theory of computation. Such ideas include learning in the limit, learning by enumeration, and probably approximately correct (pac) learning. These models usually are not suitable in practical situations. In contrast, statistics based inference methods have enjoyed a long and distinguished career. Currently, Bayesian reasoning in various forms, minimum message length (MML) and minimum description length (MDL), are widely applied approaches. They are the tools to use with particular machine learning praxis such as simulated annealing, genetic algorithms, genetic programming, artificial neural networks, and the like. These statistical inference methods select the hypothesis which minimizes the sum of the length of the description of the hypothesis (also called \u2018model\u2019) and the length of the description of the data relative to the hypothesis. It appears to us that the future of computational machine learning will include combinations of the approaches above coupled with guaranties with respect to used time and memory resources. Computational learning theory will move closer to practice and the application of the principles such as MDL require further justification. Here, we survey some of the actors in this dichotomy between theory and praxis, we justify MDL via the Bayesian approach, and give a comparison between pac learning and MDL learning of decision trees.", 
    "editor": [
      {
        "familyName": "van Leeuwen", 
        "givenName": "Jan", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/bfb0015264", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-540-60105-0", 
        "978-3-540-49435-5"
      ], 
      "name": "Computer Science Today", 
      "type": "Book"
    }, 
    "name": "Computational machine learning in theory and praxis", 
    "pagination": "518-535", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/bfb0015264"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "63169614c75f6231c744201485c770f5fcc9a94fecc57f55ebf0778038ddafb4"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1020796250"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/bfb0015264", 
      "https://app.dimensions.ai/details/publication/pub.1020796250"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T12:31", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8663_00000256.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/BFb0015264"
  }
]
 

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/bfb0015264'

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/bfb0015264'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/bfb0015264'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/bfb0015264'


 

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

102 TRIPLES      23 PREDICATES      36 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/bfb0015264 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Ncd38c35a4e46413f81523811d4512269
4 schema:citation https://doi.org/10.1016/0005-1098(78)90005-5
5 https://doi.org/10.1016/0022-0000(92)90026-f
6 https://doi.org/10.1016/0890-5401(89)90010-2
7 https://doi.org/10.1016/s0019-9958(67)91165-5
8 https://doi.org/10.1070/rm1970v025n06abeh001269
9 https://doi.org/10.1109/tit.1978.1055913
10 https://doi.org/10.1109/tit.1984.1056936
11 https://doi.org/10.1137/0220056
12 https://doi.org/10.1145/1968.1972
13 schema:datePublished 1995
14 schema:datePublishedReg 1995-01-01
15 schema:description In the last few decades a computational approach to machine learning has emerged based on paradigms from recursion theory and the theory of computation. Such ideas include learning in the limit, learning by enumeration, and probably approximately correct (pac) learning. These models usually are not suitable in practical situations. In contrast, statistics based inference methods have enjoyed a long and distinguished career. Currently, Bayesian reasoning in various forms, minimum message length (MML) and minimum description length (MDL), are widely applied approaches. They are the tools to use with particular machine learning praxis such as simulated annealing, genetic algorithms, genetic programming, artificial neural networks, and the like. These statistical inference methods select the hypothesis which minimizes the sum of the length of the description of the hypothesis (also called ‘model’) and the length of the description of the data relative to the hypothesis. It appears to us that the future of computational machine learning will include combinations of the approaches above coupled with guaranties with respect to used time and memory resources. Computational learning theory will move closer to practice and the application of the principles such as MDL require further justification. Here, we survey some of the actors in this dichotomy between theory and praxis, we justify MDL via the Bayesian approach, and give a comparison between pac learning and MDL learning of decision trees.
16 schema:editor Ne302569f8fae4ca0a458ffb9703f30f4
17 schema:genre chapter
18 schema:inLanguage en
19 schema:isAccessibleForFree true
20 schema:isPartOf N64aac94479fb40c28c885e94bb7eae6a
21 schema:name Computational machine learning in theory and praxis
22 schema:pagination 518-535
23 schema:productId N5d667205d3c14895a174f3003a80a3c8
24 N81b4af86b2b14ed794593da9ab3f965f
25 N84b25130a6c34e16b7ee066d9baafad6
26 schema:publisher N0d947b0d03494129ac062a47facb2ca1
27 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020796250
28 https://doi.org/10.1007/bfb0015264
29 schema:sdDatePublished 2019-04-15T12:31
30 schema:sdLicense https://scigraph.springernature.com/explorer/license/
31 schema:sdPublisher N41ec669c1e394777bc63adc68ea43559
32 schema:url http://link.springer.com/10.1007/BFb0015264
33 sgo:license sg:explorer/license/
34 sgo:sdDataset chapters
35 rdf:type schema:Chapter
36 N0d947b0d03494129ac062a47facb2ca1 schema:location Berlin, Heidelberg
37 schema:name Springer Berlin Heidelberg
38 rdf:type schema:Organisation
39 N2ce542309cc0405a8a9fbcf135e6019e schema:familyName van Leeuwen
40 schema:givenName Jan
41 rdf:type schema:Person
42 N41ec669c1e394777bc63adc68ea43559 schema:name Springer Nature - SN SciGraph project
43 rdf:type schema:Organization
44 N4d21ef1916284be4b13bb0410d706e27 rdf:first sg:person.014213763741.01
45 rdf:rest rdf:nil
46 N5d667205d3c14895a174f3003a80a3c8 schema:name doi
47 schema:value 10.1007/bfb0015264
48 rdf:type schema:PropertyValue
49 N64aac94479fb40c28c885e94bb7eae6a schema:isbn 978-3-540-49435-5
50 978-3-540-60105-0
51 schema:name Computer Science Today
52 rdf:type schema:Book
53 N81b4af86b2b14ed794593da9ab3f965f schema:name readcube_id
54 schema:value 63169614c75f6231c744201485c770f5fcc9a94fecc57f55ebf0778038ddafb4
55 rdf:type schema:PropertyValue
56 N84b25130a6c34e16b7ee066d9baafad6 schema:name dimensions_id
57 schema:value pub.1020796250
58 rdf:type schema:PropertyValue
59 Ncd38c35a4e46413f81523811d4512269 rdf:first sg:person.0621576316.79
60 rdf:rest N4d21ef1916284be4b13bb0410d706e27
61 Ne302569f8fae4ca0a458ffb9703f30f4 rdf:first N2ce542309cc0405a8a9fbcf135e6019e
62 rdf:rest rdf:nil
63 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
64 schema:name Information and Computing Sciences
65 rdf:type schema:DefinedTerm
66 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
67 schema:name Artificial Intelligence and Image Processing
68 rdf:type schema:DefinedTerm
69 sg:person.014213763741.01 schema:affiliation https://www.grid.ac/institutes/grid.7177.6
70 schema:familyName Vitányi
71 schema:givenName Paul
72 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014213763741.01
73 rdf:type schema:Person
74 sg:person.0621576316.79 schema:affiliation https://www.grid.ac/institutes/grid.46078.3d
75 schema:familyName Li
76 schema:givenName Ming
77 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0621576316.79
78 rdf:type schema:Person
79 https://doi.org/10.1016/0005-1098(78)90005-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018373874
80 rdf:type schema:CreativeWork
81 https://doi.org/10.1016/0022-0000(92)90026-f schema:sameAs https://app.dimensions.ai/details/publication/pub.1025072502
82 rdf:type schema:CreativeWork
83 https://doi.org/10.1016/0890-5401(89)90010-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017419784
84 rdf:type schema:CreativeWork
85 https://doi.org/10.1016/s0019-9958(67)91165-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006283457
86 rdf:type schema:CreativeWork
87 https://doi.org/10.1070/rm1970v025n06abeh001269 schema:sameAs https://app.dimensions.ai/details/publication/pub.1058193982
88 rdf:type schema:CreativeWork
89 https://doi.org/10.1109/tit.1978.1055913 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061648116
90 rdf:type schema:CreativeWork
91 https://doi.org/10.1109/tit.1984.1056936 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061649057
92 rdf:type schema:CreativeWork
93 https://doi.org/10.1137/0220056 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062842316
94 rdf:type schema:CreativeWork
95 https://doi.org/10.1145/1968.1972 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038881641
96 rdf:type schema:CreativeWork
97 https://www.grid.ac/institutes/grid.46078.3d schema:alternateName University of Waterloo
98 schema:name Computer Science Department, University of Waterloo, N2L 3G1 Waterloo, Ontario, Canada
99 rdf:type schema:Organization
100 https://www.grid.ac/institutes/grid.7177.6 schema:alternateName University of Amsterdam
101 schema:name CWI and University of Amsterdam, Kruislaan 413, 1098 SJ Amsterdam, The Netherlands
102 rdf:type schema:Organization
 




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


...