Rule Extraction from Neural Network Using Input Data Ranges Recursively View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-01

AUTHORS

Manomita Chakraborty, Saroj Kumar Biswas, Biswajit Purkayastha

ABSTRACT

Neural network is one of the best tools for data mining tasks due to its high accuracy. However, one of the drawbacks of neural network is its black box nature. This limitation makes neural network useless for many applications which require transparency in their decision-making process. Many algorithms have been proposed to overcome this drawback by extracting transparent rules from neural network, but still researchers are in search for algorithms that can generate more accurate and simple rules. Therefore, this paper proposes a rule extraction algorithm named Eclectic Rule Extraction from Neural Network Recursively (ERENNR), with the aim to generate simple and accurate rules. ERENNR algorithm extracts symbolic classification rules from a single-layer feed-forward neural network. The novelty of this algorithm lies in its procedure of analyzing the nodes of the network. It analyzes a hidden node based on data ranges of input attributes with respect to its output and analyzes an output node using logical combination of the outputs of hidden nodes with respect to output class. And finally it generates a rule set by proceeding in a backward direction starting from the output layer. For each rule in the set, it repeats the whole process of rule extraction if the rule satisfies certain criteria. The algorithm is validated with eleven benchmark datasets. Experimental results show that the generated rules are simple and accurate. More... »

PAGES

1-30

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00354-018-0048-0

DOI

http://dx.doi.org/10.1007/s00354-018-0048-0

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1109810627


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": "National Institute Of Technology Silchar", 
          "id": "https://www.grid.ac/institutes/grid.444720.1", 
          "name": [
            "Computer Science and Engineering Department, National Institute of Technology Silchar, 788010, Silchar, Assam, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Chakraborty", 
        "givenName": "Manomita", 
        "id": "sg:person.07771413026.87", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07771413026.87"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "National Institute Of Technology Silchar", 
          "id": "https://www.grid.ac/institutes/grid.444720.1", 
          "name": [
            "Computer Science and Engineering Department, National Institute of Technology Silchar, 788010, Silchar, Assam, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Biswas", 
        "givenName": "Saroj Kumar", 
        "id": "sg:person.013234227104.01", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013234227104.01"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "National Institute Of Technology Silchar", 
          "id": "https://www.grid.ac/institutes/grid.444720.1", 
          "name": [
            "Computer Science and Engineering Department, National Institute of Technology Silchar, 788010, Silchar, Assam, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Purkayastha", 
        "givenName": "Biswajit", 
        "id": "sg:person.016104762417.40", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016104762417.40"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.orp.2016.08.001", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003301750"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf02944803", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1012974799", 
          "https://doi.org/10.1007/bf02944803"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf02944803", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1012974799", 
          "https://doi.org/10.1007/bf02944803"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00993103", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017737903", 
          "https://doi.org/10.1007/bf00993103"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00500-016-2312-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018085932", 
          "https://doi.org/10.1007/s00500-016-2312-x"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00500-016-2312-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018085932", 
          "https://doi.org/10.1007/s00500-016-2312-x"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neunet.2008.01.003", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030241718"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0925-2312(97)00038-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1031515242"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/neco.1997.9.1.205", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033202298"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11063-011-9207-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034441287", 
          "https://doi.org/10.1007/s11063-011-9207-8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.imu.2015.12.003", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038104540"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1008307919726", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042615414", 
          "https://doi.org/10.1023/a:1008307919726"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.imu.2016.02.001", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053015835"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/2.485895", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061105570"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/69.774103", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061213767"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tnn.2005.863472", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061716988"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tnn.2007.908641", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061717303"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tnnls.2015.2389037", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061718764"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1142/s0218213017500063", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062965084"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icece.2012.6471502", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093762392"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccae.2010.5451981", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094065973"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/ictta.2006.1684577", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094959022"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/ijcnn.2012.6252446", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095169359"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00354-018-0031-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100993572", 
          "https://doi.org/10.1007/s00354-018-0031-9"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-01", 
    "datePublishedReg": "2019-01-01", 
    "description": "Neural network is one of the best tools for data mining tasks due to its high accuracy. However, one of the drawbacks of neural network is its black box nature. This limitation makes neural network useless for many applications which require transparency in their decision-making process. Many algorithms have been proposed to overcome this drawback by extracting transparent rules from neural network, but still researchers are in search for algorithms that can generate more accurate and simple rules. Therefore, this paper proposes a rule extraction algorithm named Eclectic Rule Extraction from Neural Network Recursively (ERENNR), with the aim to generate simple and accurate rules. ERENNR algorithm extracts symbolic classification rules from a single-layer feed-forward neural network. The novelty of this algorithm lies in its procedure of analyzing the nodes of the network. It analyzes a hidden node based on data ranges of input attributes with respect to its output and analyzes an output node using logical combination of the outputs of hidden nodes with respect to output class. And finally it generates a rule set by proceeding in a backward direction starting from the output layer. For each rule in the set, it repeats the whole process of rule extraction if the rule satisfies certain criteria. The algorithm is validated with eleven benchmark datasets. Experimental results show that the generated rules are simple and accurate.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s00354-018-0048-0", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1053619", 
        "issn": [
          "0288-3635", 
          "1882-7055"
        ], 
        "name": "New Generation Computing", 
        "type": "Periodical"
      }
    ], 
    "name": "Rule Extraction from Neural Network Using Input Data Ranges Recursively", 
    "pagination": "1-30", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "410c823d4491df0b6ba09ff1ac5db9c8360b24b3d2fa97887e96d3323d322597"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00354-018-0048-0"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1109810627"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00354-018-0048-0", 
      "https://app.dimensions.ai/details/publication/pub.1109810627"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-10T14:24", 
    "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_8660_00000610.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs00354-018-0048-0"
  }
]
 

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/s00354-018-0048-0'

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/s00354-018-0048-0'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00354-018-0048-0'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00354-018-0048-0'


 

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

141 TRIPLES      21 PREDICATES      47 URIs      17 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00354-018-0048-0 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Ne8d303a072af4ea9867e6d207c3c12a4
4 schema:citation sg:pub.10.1007/bf00993103
5 sg:pub.10.1007/bf02944803
6 sg:pub.10.1007/s00354-018-0031-9
7 sg:pub.10.1007/s00500-016-2312-x
8 sg:pub.10.1007/s11063-011-9207-8
9 sg:pub.10.1023/a:1008307919726
10 https://doi.org/10.1016/j.imu.2015.12.003
11 https://doi.org/10.1016/j.imu.2016.02.001
12 https://doi.org/10.1016/j.neunet.2008.01.003
13 https://doi.org/10.1016/j.orp.2016.08.001
14 https://doi.org/10.1016/s0925-2312(97)00038-6
15 https://doi.org/10.1109/2.485895
16 https://doi.org/10.1109/69.774103
17 https://doi.org/10.1109/iccae.2010.5451981
18 https://doi.org/10.1109/icece.2012.6471502
19 https://doi.org/10.1109/ictta.2006.1684577
20 https://doi.org/10.1109/ijcnn.2012.6252446
21 https://doi.org/10.1109/tnn.2005.863472
22 https://doi.org/10.1109/tnn.2007.908641
23 https://doi.org/10.1109/tnnls.2015.2389037
24 https://doi.org/10.1142/s0218213017500063
25 https://doi.org/10.1162/neco.1997.9.1.205
26 schema:datePublished 2019-01
27 schema:datePublishedReg 2019-01-01
28 schema:description Neural network is one of the best tools for data mining tasks due to its high accuracy. However, one of the drawbacks of neural network is its black box nature. This limitation makes neural network useless for many applications which require transparency in their decision-making process. Many algorithms have been proposed to overcome this drawback by extracting transparent rules from neural network, but still researchers are in search for algorithms that can generate more accurate and simple rules. Therefore, this paper proposes a rule extraction algorithm named Eclectic Rule Extraction from Neural Network Recursively (ERENNR), with the aim to generate simple and accurate rules. ERENNR algorithm extracts symbolic classification rules from a single-layer feed-forward neural network. The novelty of this algorithm lies in its procedure of analyzing the nodes of the network. It analyzes a hidden node based on data ranges of input attributes with respect to its output and analyzes an output node using logical combination of the outputs of hidden nodes with respect to output class. And finally it generates a rule set by proceeding in a backward direction starting from the output layer. For each rule in the set, it repeats the whole process of rule extraction if the rule satisfies certain criteria. The algorithm is validated with eleven benchmark datasets. Experimental results show that the generated rules are simple and accurate.
29 schema:genre research_article
30 schema:inLanguage en
31 schema:isAccessibleForFree false
32 schema:isPartOf sg:journal.1053619
33 schema:name Rule Extraction from Neural Network Using Input Data Ranges Recursively
34 schema:pagination 1-30
35 schema:productId N4d19d0c55fbf4b8c8dc72b10ede66745
36 N8bbe118241c84d6d993ad755790625b9
37 Nae1aa72f30274081b02b408636375d84
38 schema:sameAs https://app.dimensions.ai/details/publication/pub.1109810627
39 https://doi.org/10.1007/s00354-018-0048-0
40 schema:sdDatePublished 2019-04-10T14:24
41 schema:sdLicense https://scigraph.springernature.com/explorer/license/
42 schema:sdPublisher N7ae5c9a28ec7494fa496be580c24a4f5
43 schema:url https://link.springer.com/10.1007%2Fs00354-018-0048-0
44 sgo:license sg:explorer/license/
45 sgo:sdDataset articles
46 rdf:type schema:ScholarlyArticle
47 N4d19d0c55fbf4b8c8dc72b10ede66745 schema:name readcube_id
48 schema:value 410c823d4491df0b6ba09ff1ac5db9c8360b24b3d2fa97887e96d3323d322597
49 rdf:type schema:PropertyValue
50 N558ccc583aa24240811d46b7ebe97f7f rdf:first sg:person.013234227104.01
51 rdf:rest N919b9aa4b8cf412b8b67c82528ca9909
52 N7ae5c9a28ec7494fa496be580c24a4f5 schema:name Springer Nature - SN SciGraph project
53 rdf:type schema:Organization
54 N8bbe118241c84d6d993ad755790625b9 schema:name dimensions_id
55 schema:value pub.1109810627
56 rdf:type schema:PropertyValue
57 N919b9aa4b8cf412b8b67c82528ca9909 rdf:first sg:person.016104762417.40
58 rdf:rest rdf:nil
59 Nae1aa72f30274081b02b408636375d84 schema:name doi
60 schema:value 10.1007/s00354-018-0048-0
61 rdf:type schema:PropertyValue
62 Ne8d303a072af4ea9867e6d207c3c12a4 rdf:first sg:person.07771413026.87
63 rdf:rest N558ccc583aa24240811d46b7ebe97f7f
64 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
65 schema:name Information and Computing Sciences
66 rdf:type schema:DefinedTerm
67 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
68 schema:name Artificial Intelligence and Image Processing
69 rdf:type schema:DefinedTerm
70 sg:journal.1053619 schema:issn 0288-3635
71 1882-7055
72 schema:name New Generation Computing
73 rdf:type schema:Periodical
74 sg:person.013234227104.01 schema:affiliation https://www.grid.ac/institutes/grid.444720.1
75 schema:familyName Biswas
76 schema:givenName Saroj Kumar
77 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013234227104.01
78 rdf:type schema:Person
79 sg:person.016104762417.40 schema:affiliation https://www.grid.ac/institutes/grid.444720.1
80 schema:familyName Purkayastha
81 schema:givenName Biswajit
82 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016104762417.40
83 rdf:type schema:Person
84 sg:person.07771413026.87 schema:affiliation https://www.grid.ac/institutes/grid.444720.1
85 schema:familyName Chakraborty
86 schema:givenName Manomita
87 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07771413026.87
88 rdf:type schema:Person
89 sg:pub.10.1007/bf00993103 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017737903
90 https://doi.org/10.1007/bf00993103
91 rdf:type schema:CreativeWork
92 sg:pub.10.1007/bf02944803 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012974799
93 https://doi.org/10.1007/bf02944803
94 rdf:type schema:CreativeWork
95 sg:pub.10.1007/s00354-018-0031-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100993572
96 https://doi.org/10.1007/s00354-018-0031-9
97 rdf:type schema:CreativeWork
98 sg:pub.10.1007/s00500-016-2312-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1018085932
99 https://doi.org/10.1007/s00500-016-2312-x
100 rdf:type schema:CreativeWork
101 sg:pub.10.1007/s11063-011-9207-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034441287
102 https://doi.org/10.1007/s11063-011-9207-8
103 rdf:type schema:CreativeWork
104 sg:pub.10.1023/a:1008307919726 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042615414
105 https://doi.org/10.1023/a:1008307919726
106 rdf:type schema:CreativeWork
107 https://doi.org/10.1016/j.imu.2015.12.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038104540
108 rdf:type schema:CreativeWork
109 https://doi.org/10.1016/j.imu.2016.02.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053015835
110 rdf:type schema:CreativeWork
111 https://doi.org/10.1016/j.neunet.2008.01.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030241718
112 rdf:type schema:CreativeWork
113 https://doi.org/10.1016/j.orp.2016.08.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003301750
114 rdf:type schema:CreativeWork
115 https://doi.org/10.1016/s0925-2312(97)00038-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031515242
116 rdf:type schema:CreativeWork
117 https://doi.org/10.1109/2.485895 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061105570
118 rdf:type schema:CreativeWork
119 https://doi.org/10.1109/69.774103 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061213767
120 rdf:type schema:CreativeWork
121 https://doi.org/10.1109/iccae.2010.5451981 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094065973
122 rdf:type schema:CreativeWork
123 https://doi.org/10.1109/icece.2012.6471502 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093762392
124 rdf:type schema:CreativeWork
125 https://doi.org/10.1109/ictta.2006.1684577 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094959022
126 rdf:type schema:CreativeWork
127 https://doi.org/10.1109/ijcnn.2012.6252446 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095169359
128 rdf:type schema:CreativeWork
129 https://doi.org/10.1109/tnn.2005.863472 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061716988
130 rdf:type schema:CreativeWork
131 https://doi.org/10.1109/tnn.2007.908641 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061717303
132 rdf:type schema:CreativeWork
133 https://doi.org/10.1109/tnnls.2015.2389037 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061718764
134 rdf:type schema:CreativeWork
135 https://doi.org/10.1142/s0218213017500063 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062965084
136 rdf:type schema:CreativeWork
137 https://doi.org/10.1162/neco.1997.9.1.205 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033202298
138 rdf:type schema:CreativeWork
139 https://www.grid.ac/institutes/grid.444720.1 schema:alternateName National Institute Of Technology Silchar
140 schema:name Computer Science and Engineering Department, National Institute of Technology Silchar, 788010, Silchar, Assam, India
141 rdf:type schema:Organization
 




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


...