Fast Robust Learning Algorithm Dedicated to LMLS Criterion View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2010

AUTHORS

Andrzej Rusiecki

ABSTRACT

Robust neural network learning algorithms are often applied to deal with the problem of gross errors and outliers. Unfortunately, such methods suffer from high computational complexity, which makes them ineffective. In this paper, we propose a new robust learning algorithm based on the LMLS (Least Mean Log Squares) error criterion. It can be considered, as a good trade-off between robustness to outliers and learning efficiency. As it was experimentally demonstrated, the novel method is not only faster but also more robust than the LMLS algorithm. Results of implementation and simulation of nets trained with the new algorithm, the traditional backpropagation (BP) algorithm and robust LMLS method are presented and compared. More... »

PAGES

96-103

Book

TITLE

Artifical Intelligence and Soft Computing

ISBN

978-3-642-13231-5
978-3-642-13232-2

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-13232-2_13

DOI

http://dx.doi.org/10.1007/978-3-642-13232-2_13

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1004101266


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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Wroclaw University of Technology, Wroclaw, Poland", 
          "id": "http://www.grid.ac/institutes/grid.7005.2", 
          "name": [
            "Wroclaw University of Technology, Wroclaw, Poland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Rusiecki", 
        "givenName": "Andrzej", 
        "id": "sg:person.016031766473.38", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016031766473.38"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2010", 
    "datePublishedReg": "2010-01-01", 
    "description": "Robust neural network learning algorithms are often applied to deal with the problem of gross errors and outliers. Unfortunately, such methods suffer from high computational complexity, which makes them ineffective. In this paper, we propose a new robust learning algorithm based on the LMLS (Least Mean Log Squares) error criterion. It can be considered, as a good trade-off between robustness to outliers and learning efficiency. As it was experimentally demonstrated, the novel method is not only faster but also more robust than the LMLS algorithm. Results of implementation and simulation of nets trained with the new algorithm, the traditional backpropagation (BP) algorithm and robust LMLS method are presented and compared.", 
    "editor": [
      {
        "familyName": "Rutkowski", 
        "givenName": "Leszek", 
        "type": "Person"
      }, 
      {
        "familyName": "Scherer", 
        "givenName": "Rafa\u0142", 
        "type": "Person"
      }, 
      {
        "familyName": "Tadeusiewicz", 
        "givenName": "Ryszard", 
        "type": "Person"
      }, 
      {
        "familyName": "Zadeh", 
        "givenName": "Lotfi A.", 
        "type": "Person"
      }, 
      {
        "familyName": "Zurada", 
        "givenName": "Jacek M.", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-13232-2_13", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-642-13231-5", 
        "978-3-642-13232-2"
      ], 
      "name": "Artifical Intelligence and Soft Computing", 
      "type": "Book"
    }, 
    "keywords": [
      "robust learning algorithm", 
      "learning algorithm", 
      "new robust learning algorithm", 
      "robust neural network", 
      "high computational complexity", 
      "traditional backpropagation algorithm", 
      "neural network", 
      "computational complexity", 
      "backpropagation algorithm", 
      "results of implementation", 
      "algorithm", 
      "new algorithm", 
      "such methods", 
      "error criterion", 
      "novel method", 
      "outliers", 
      "gross errors", 
      "network", 
      "complexity", 
      "robustness", 
      "implementation", 
      "nets", 
      "method", 
      "error", 
      "simulations", 
      "efficiency", 
      "criteria", 
      "results", 
      "problem", 
      "paper"
    ], 
    "name": "Fast Robust Learning Algorithm Dedicated to LMLS Criterion", 
    "pagination": "96-103", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1004101266"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-13232-2_13"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-13232-2_13", 
      "https://app.dimensions.ai/details/publication/pub.1004101266"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-09-02T16:13", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220902/entities/gbq_results/chapter/chapter_308.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-642-13232-2_13"
  }
]
 

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.10.1007/978-3-642-13232-2_13'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-13232-2_13'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-13232-2_13'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-13232-2_13'


 

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

109 TRIPLES      22 PREDICATES      55 URIs      48 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-13232-2_13 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N03b8216f97c54ad0812e5b71e94a4816
4 schema:datePublished 2010
5 schema:datePublishedReg 2010-01-01
6 schema:description Robust neural network learning algorithms are often applied to deal with the problem of gross errors and outliers. Unfortunately, such methods suffer from high computational complexity, which makes them ineffective. In this paper, we propose a new robust learning algorithm based on the LMLS (Least Mean Log Squares) error criterion. It can be considered, as a good trade-off between robustness to outliers and learning efficiency. As it was experimentally demonstrated, the novel method is not only faster but also more robust than the LMLS algorithm. Results of implementation and simulation of nets trained with the new algorithm, the traditional backpropagation (BP) algorithm and robust LMLS method are presented and compared.
7 schema:editor N2c1cc36e416b4c8cab9f5cc3c9378ff7
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf N7260d577c6064ecaa73c80344086c0bc
11 schema:keywords algorithm
12 backpropagation algorithm
13 complexity
14 computational complexity
15 criteria
16 efficiency
17 error
18 error criterion
19 gross errors
20 high computational complexity
21 implementation
22 learning algorithm
23 method
24 nets
25 network
26 neural network
27 new algorithm
28 new robust learning algorithm
29 novel method
30 outliers
31 paper
32 problem
33 results
34 results of implementation
35 robust learning algorithm
36 robust neural network
37 robustness
38 simulations
39 such methods
40 traditional backpropagation algorithm
41 schema:name Fast Robust Learning Algorithm Dedicated to LMLS Criterion
42 schema:pagination 96-103
43 schema:productId Nfd19cb7495084dc8a17c76e015030d59
44 Nff2980019b894f7eaa8faca71d9d5daa
45 schema:publisher N5defaf22d2774bc89faf6924e2521d4f
46 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004101266
47 https://doi.org/10.1007/978-3-642-13232-2_13
48 schema:sdDatePublished 2022-09-02T16:13
49 schema:sdLicense https://scigraph.springernature.com/explorer/license/
50 schema:sdPublisher N34940e4b9cd64b8b90ee582c7a763900
51 schema:url https://doi.org/10.1007/978-3-642-13232-2_13
52 sgo:license sg:explorer/license/
53 sgo:sdDataset chapters
54 rdf:type schema:Chapter
55 N03b8216f97c54ad0812e5b71e94a4816 rdf:first sg:person.016031766473.38
56 rdf:rest rdf:nil
57 N11845a5d354444478f75c21260ac1461 schema:familyName Tadeusiewicz
58 schema:givenName Ryszard
59 rdf:type schema:Person
60 N156cf6f3c6a14b358dab27b6474919b2 schema:familyName Zurada
61 schema:givenName Jacek M.
62 rdf:type schema:Person
63 N1bd0b72e87d14a5f88ce14dbd6a57968 schema:familyName Rutkowski
64 schema:givenName Leszek
65 rdf:type schema:Person
66 N2c1cc36e416b4c8cab9f5cc3c9378ff7 rdf:first N1bd0b72e87d14a5f88ce14dbd6a57968
67 rdf:rest Nc6fc8186a0e3453ca65f0e69cfb17236
68 N34940e4b9cd64b8b90ee582c7a763900 schema:name Springer Nature - SN SciGraph project
69 rdf:type schema:Organization
70 N51641c2bacff4125a44aff0b4019bae3 rdf:first Nba356004a1cf4a7c817ff197a84048c3
71 rdf:rest Na6f1f16cc1f14c00a6a3a3e18ce3bc20
72 N5defaf22d2774bc89faf6924e2521d4f schema:name Springer Nature
73 rdf:type schema:Organisation
74 N60c3f19915a64bc39e91718085960090 schema:familyName Scherer
75 schema:givenName Rafał
76 rdf:type schema:Person
77 N7260d577c6064ecaa73c80344086c0bc schema:isbn 978-3-642-13231-5
78 978-3-642-13232-2
79 schema:name Artifical Intelligence and Soft Computing
80 rdf:type schema:Book
81 Na6f1f16cc1f14c00a6a3a3e18ce3bc20 rdf:first N156cf6f3c6a14b358dab27b6474919b2
82 rdf:rest rdf:nil
83 Nba356004a1cf4a7c817ff197a84048c3 schema:familyName Zadeh
84 schema:givenName Lotfi A.
85 rdf:type schema:Person
86 Nc6fc8186a0e3453ca65f0e69cfb17236 rdf:first N60c3f19915a64bc39e91718085960090
87 rdf:rest Nf6e31980cc4147df931b89c7b8fdb94e
88 Nf6e31980cc4147df931b89c7b8fdb94e rdf:first N11845a5d354444478f75c21260ac1461
89 rdf:rest N51641c2bacff4125a44aff0b4019bae3
90 Nfd19cb7495084dc8a17c76e015030d59 schema:name doi
91 schema:value 10.1007/978-3-642-13232-2_13
92 rdf:type schema:PropertyValue
93 Nff2980019b894f7eaa8faca71d9d5daa schema:name dimensions_id
94 schema:value pub.1004101266
95 rdf:type schema:PropertyValue
96 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
97 schema:name Information and Computing Sciences
98 rdf:type schema:DefinedTerm
99 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
100 schema:name Artificial Intelligence and Image Processing
101 rdf:type schema:DefinedTerm
102 sg:person.016031766473.38 schema:affiliation grid-institutes:grid.7005.2
103 schema:familyName Rusiecki
104 schema:givenName Andrzej
105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016031766473.38
106 rdf:type schema:Person
107 grid-institutes:grid.7005.2 schema:alternateName Wroclaw University of Technology, Wroclaw, Poland
108 schema:name Wroclaw University of Technology, Wroclaw, Poland
109 rdf:type schema:Organization
 




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


...