An ant colony optimization algorithm for continuous optimization: application to feed-forward neural network training View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2007-03-02

AUTHORS

Krzysztof Socha, Christian Blum

ABSTRACT

Ant colony optimization (ACO) is an optimization technique that was inspired by the foraging behaviour of real ant colonies. Originally, the method was introduced for the application to discrete optimization problems. Recently we proposed a first ACO variant for continuous optimization. In this work we choose the training of feed-forward neural networks for pattern classification as a test case for this algorithm. In addition, we propose hybrid algorithm variants that incorporate short runs of classical gradient techniques such as backpropagation. For evaluating our algorithms we apply them to classification problems from the medical field, and compare the results to some basic algorithms from the literature. The results show, first, that the best of our algorithms are comparable to gradient-based algorithms for neural network training, and second, that our algorithms compare favorably with a basic genetic algorithm. More... »

PAGES

235-247

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00521-007-0084-z

DOI

http://dx.doi.org/10.1007/s00521-007-0084-z

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1046650841


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": "IRIDIA, CoDE, Universit\u00e9 Libre de Bruxelles, Brussels, Belgium", 
          "id": "http://www.grid.ac/institutes/grid.4989.c", 
          "name": [
            "IRIDIA, CoDE, Universit\u00e9 Libre de Bruxelles, Brussels, Belgium"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Socha", 
        "givenName": "Krzysztof", 
        "id": "sg:person.013702020002.24", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013702020002.24"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "ALBCOM, LSI, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain", 
          "id": "http://www.grid.ac/institutes/grid.6835.8", 
          "name": [
            "ALBCOM, LSI, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Blum", 
        "givenName": "Christian", 
        "id": "sg:person.011315326455.07", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011315326455.07"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/bf01417909", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037253466", 
          "https://doi.org/10.1007/bf01417909"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/0-387-33416-5_8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030305707", 
          "https://doi.org/10.1007/0-387-33416-5_8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-24854-5_87", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000268145", 
          "https://doi.org/10.1007/978-3-540-24854-5_87"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4615-1539-5_18", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030622301", 
          "https://doi.org/10.1007/978-1-4615-1539-5_18"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-28646-2_3", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034355397", 
          "https://doi.org/10.1007/978-3-540-28646-2_3"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-45105-6_5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034800629", 
          "https://doi.org/10.1007/3-540-45105-6_5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-36970-8_33", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025091845", 
          "https://doi.org/10.1007/3-540-36970-8_33"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-45724-0_18", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037503246", 
          "https://doi.org/10.1007/3-540-45724-0_18"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-0-387-21606-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022356842", 
          "https://doi.org/10.1007/978-0-387-21606-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-60469-3_22", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018468505", 
          "https://doi.org/10.1007/3-540-60469-3_22"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/b99492", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034461735", 
          "https://doi.org/10.1007/b99492"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2007-03-02", 
    "datePublishedReg": "2007-03-02", 
    "description": "Ant colony optimization (ACO) is an optimization technique that was inspired by the foraging behaviour of real ant colonies. Originally, the method was introduced for the application to discrete optimization problems. Recently we proposed a first ACO variant for continuous optimization. In this work we choose the training of feed-forward neural networks for pattern classification as a test case for this algorithm. In addition, we propose hybrid algorithm variants that incorporate short runs of classical gradient techniques such as backpropagation. For evaluating our algorithms we apply them to classification problems from the medical field, and compare the results to some basic algorithms from the literature. The results show, first, that the best of our algorithms are comparable to gradient-based algorithms for neural network training, and second, that our algorithms compare favorably with a basic genetic algorithm.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s00521-007-0084-z", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1104357", 
        "issn": [
          "0941-0643", 
          "1433-3058"
        ], 
        "name": "Neural Computing and Applications", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "3", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "16"
      }
    ], 
    "keywords": [
      "neural network training", 
      "Ant Colony Optimization", 
      "network training", 
      "continuous optimization", 
      "training of feed", 
      "ant colony optimization algorithm", 
      "gradient-based algorithm", 
      "colony optimization algorithm", 
      "real ant colonies", 
      "basic genetic algorithm", 
      "neural network", 
      "classification problem", 
      "ACO variants", 
      "colony optimization", 
      "pattern classification", 
      "algorithm variants", 
      "basic algorithm", 
      "genetic algorithm", 
      "algorithm", 
      "optimization algorithm", 
      "optimization problem", 
      "optimization techniques", 
      "ant colonies", 
      "test cases", 
      "classical gradient techniques", 
      "medical field", 
      "optimization", 
      "backpropagation", 
      "gradient technique", 
      "applications", 
      "network", 
      "technique", 
      "training", 
      "classification", 
      "work", 
      "foraging behaviour", 
      "method", 
      "results", 
      "variants", 
      "run", 
      "field", 
      "literature", 
      "behavior", 
      "addition", 
      "cases", 
      "problem", 
      "feed", 
      "colonies", 
      "short run", 
      "first ACO variant", 
      "hybrid algorithm variants", 
      "feed-forward neural network training"
    ], 
    "name": "An ant colony optimization algorithm for continuous optimization: application to feed-forward neural network training", 
    "pagination": "235-247", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1046650841"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00521-007-0084-z"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00521-007-0084-z", 
      "https://app.dimensions.ai/details/publication/pub.1046650841"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-01-01T18:17", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/article/article_447.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s00521-007-0084-z"
  }
]
 

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/s00521-007-0084-z'

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/s00521-007-0084-z'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00521-007-0084-z'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00521-007-0084-z'


 

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

164 TRIPLES      22 PREDICATES      88 URIs      69 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00521-007-0084-z schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N199fe29434f34624849b3288a0dcb9ea
4 schema:citation sg:pub.10.1007/0-387-33416-5_8
5 sg:pub.10.1007/3-540-36970-8_33
6 sg:pub.10.1007/3-540-45105-6_5
7 sg:pub.10.1007/3-540-45724-0_18
8 sg:pub.10.1007/3-540-60469-3_22
9 sg:pub.10.1007/978-0-387-21606-5
10 sg:pub.10.1007/978-1-4615-1539-5_18
11 sg:pub.10.1007/978-3-540-24854-5_87
12 sg:pub.10.1007/978-3-540-28646-2_3
13 sg:pub.10.1007/b99492
14 sg:pub.10.1007/bf01417909
15 schema:datePublished 2007-03-02
16 schema:datePublishedReg 2007-03-02
17 schema:description Ant colony optimization (ACO) is an optimization technique that was inspired by the foraging behaviour of real ant colonies. Originally, the method was introduced for the application to discrete optimization problems. Recently we proposed a first ACO variant for continuous optimization. In this work we choose the training of feed-forward neural networks for pattern classification as a test case for this algorithm. In addition, we propose hybrid algorithm variants that incorporate short runs of classical gradient techniques such as backpropagation. For evaluating our algorithms we apply them to classification problems from the medical field, and compare the results to some basic algorithms from the literature. The results show, first, that the best of our algorithms are comparable to gradient-based algorithms for neural network training, and second, that our algorithms compare favorably with a basic genetic algorithm.
18 schema:genre article
19 schema:inLanguage en
20 schema:isAccessibleForFree false
21 schema:isPartOf N36dcf32b3bc94d82a77a0e24e6bca1fc
22 N5756fe22a94b4db98d6e8d9d8dfbbc60
23 sg:journal.1104357
24 schema:keywords ACO variants
25 Ant Colony Optimization
26 addition
27 algorithm
28 algorithm variants
29 ant colonies
30 ant colony optimization algorithm
31 applications
32 backpropagation
33 basic algorithm
34 basic genetic algorithm
35 behavior
36 cases
37 classical gradient techniques
38 classification
39 classification problem
40 colonies
41 colony optimization
42 colony optimization algorithm
43 continuous optimization
44 feed
45 feed-forward neural network training
46 field
47 first ACO variant
48 foraging behaviour
49 genetic algorithm
50 gradient technique
51 gradient-based algorithm
52 hybrid algorithm variants
53 literature
54 medical field
55 method
56 network
57 network training
58 neural network
59 neural network training
60 optimization
61 optimization algorithm
62 optimization problem
63 optimization techniques
64 pattern classification
65 problem
66 real ant colonies
67 results
68 run
69 short run
70 technique
71 test cases
72 training
73 training of feed
74 variants
75 work
76 schema:name An ant colony optimization algorithm for continuous optimization: application to feed-forward neural network training
77 schema:pagination 235-247
78 schema:productId N178c09c5176844cbbad2c68ac60bdf63
79 N2c9810dfc06041d0a35315e1bc286498
80 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046650841
81 https://doi.org/10.1007/s00521-007-0084-z
82 schema:sdDatePublished 2022-01-01T18:17
83 schema:sdLicense https://scigraph.springernature.com/explorer/license/
84 schema:sdPublisher N3134b4cb56bf438d85cea96ada574e10
85 schema:url https://doi.org/10.1007/s00521-007-0084-z
86 sgo:license sg:explorer/license/
87 sgo:sdDataset articles
88 rdf:type schema:ScholarlyArticle
89 N178c09c5176844cbbad2c68ac60bdf63 schema:name dimensions_id
90 schema:value pub.1046650841
91 rdf:type schema:PropertyValue
92 N199fe29434f34624849b3288a0dcb9ea rdf:first sg:person.013702020002.24
93 rdf:rest N8164735a11ca497083307f1d8c8fbd05
94 N2c9810dfc06041d0a35315e1bc286498 schema:name doi
95 schema:value 10.1007/s00521-007-0084-z
96 rdf:type schema:PropertyValue
97 N3134b4cb56bf438d85cea96ada574e10 schema:name Springer Nature - SN SciGraph project
98 rdf:type schema:Organization
99 N36dcf32b3bc94d82a77a0e24e6bca1fc schema:issueNumber 3
100 rdf:type schema:PublicationIssue
101 N5756fe22a94b4db98d6e8d9d8dfbbc60 schema:volumeNumber 16
102 rdf:type schema:PublicationVolume
103 N8164735a11ca497083307f1d8c8fbd05 rdf:first sg:person.011315326455.07
104 rdf:rest rdf:nil
105 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
106 schema:name Information and Computing Sciences
107 rdf:type schema:DefinedTerm
108 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
109 schema:name Artificial Intelligence and Image Processing
110 rdf:type schema:DefinedTerm
111 sg:journal.1104357 schema:issn 0941-0643
112 1433-3058
113 schema:name Neural Computing and Applications
114 schema:publisher Springer Nature
115 rdf:type schema:Periodical
116 sg:person.011315326455.07 schema:affiliation grid-institutes:grid.6835.8
117 schema:familyName Blum
118 schema:givenName Christian
119 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011315326455.07
120 rdf:type schema:Person
121 sg:person.013702020002.24 schema:affiliation grid-institutes:grid.4989.c
122 schema:familyName Socha
123 schema:givenName Krzysztof
124 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013702020002.24
125 rdf:type schema:Person
126 sg:pub.10.1007/0-387-33416-5_8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030305707
127 https://doi.org/10.1007/0-387-33416-5_8
128 rdf:type schema:CreativeWork
129 sg:pub.10.1007/3-540-36970-8_33 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025091845
130 https://doi.org/10.1007/3-540-36970-8_33
131 rdf:type schema:CreativeWork
132 sg:pub.10.1007/3-540-45105-6_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034800629
133 https://doi.org/10.1007/3-540-45105-6_5
134 rdf:type schema:CreativeWork
135 sg:pub.10.1007/3-540-45724-0_18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037503246
136 https://doi.org/10.1007/3-540-45724-0_18
137 rdf:type schema:CreativeWork
138 sg:pub.10.1007/3-540-60469-3_22 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018468505
139 https://doi.org/10.1007/3-540-60469-3_22
140 rdf:type schema:CreativeWork
141 sg:pub.10.1007/978-0-387-21606-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022356842
142 https://doi.org/10.1007/978-0-387-21606-5
143 rdf:type schema:CreativeWork
144 sg:pub.10.1007/978-1-4615-1539-5_18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030622301
145 https://doi.org/10.1007/978-1-4615-1539-5_18
146 rdf:type schema:CreativeWork
147 sg:pub.10.1007/978-3-540-24854-5_87 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000268145
148 https://doi.org/10.1007/978-3-540-24854-5_87
149 rdf:type schema:CreativeWork
150 sg:pub.10.1007/978-3-540-28646-2_3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034355397
151 https://doi.org/10.1007/978-3-540-28646-2_3
152 rdf:type schema:CreativeWork
153 sg:pub.10.1007/b99492 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034461735
154 https://doi.org/10.1007/b99492
155 rdf:type schema:CreativeWork
156 sg:pub.10.1007/bf01417909 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037253466
157 https://doi.org/10.1007/bf01417909
158 rdf:type schema:CreativeWork
159 grid-institutes:grid.4989.c schema:alternateName IRIDIA, CoDE, Université Libre de Bruxelles, Brussels, Belgium
160 schema:name IRIDIA, CoDE, Université Libre de Bruxelles, Brussels, Belgium
161 rdf:type schema:Organization
162 grid-institutes:grid.6835.8 schema:alternateName ALBCOM, LSI, Universitat Politècnica de Catalunya, Barcelona, Spain
163 schema:name ALBCOM, LSI, Universitat Politècnica de Catalunya, Barcelona, Spain
164 rdf:type schema:Organization
 




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


...