On the automated, evolutionary design of neural networks: past, present, and future View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-03-27

AUTHORS

Alejandro Baldominos, Yago Saez, Pedro Isasi

ABSTRACT

Neuroevolution is the name given to a field of computer science that applies evolutionary computation for evolving some aspects of neural networks. After the AI Winter came to an end, neural networks reemerged to solve a great variety of problems. However, their usage requires designing their topology, a decision with a potentially high impact on performance. Whereas many works have tried to suggest rules-of-thumb for designing topologies, the truth is that there are not analytic procedures for determining the optimal one for a given problem, and trial-and-error is often used instead. Neuroevolution arose almost 3 decades ago, with some works focusing on the evolutionary design of the topology and most works describing techniques for learning connection weights. Since then, evolutionary computation has been proved to be a convenient approach for determining the topology and weights of neural networks, and neuroevolution has been applied to a great variety of fields. However, for more than 2 decades neuroevolution has mainly focused on simple artificial neural networks models, far from today’s deep learning standards. This is insufficient for determining good architectures for modern networks extensively used nowadays, which involve multiple hidden layers, recurrent cells, etc. More importantly, deep and convolutional neural networks have become a de facto standard in representation learning for solving many different problems, and neuroevolution has only focused in this kind of networks in very recent years, with many works being presented in 2017 onward. In this paper, we review the field of neuroevolution during the last 3 decades. We will put the focus on very recent works on the evolution of deep and convolutional neural networks, which is a new but growing field of study. To the best of our knowledge, this is the best survey reviewing the literature in this field, and we have described the features of each work as well as their performance on well-known databases when available. This work aims to provide a complete reference of all works related to neuroevolution of convolutional neural networks up to the date. Finally, we will provide some future directions for the advancement of this research area. More... »

PAGES

1-27

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00521-019-04160-6

DOI

http://dx.doi.org/10.1007/s00521-019-04160-6

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1113042666


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": "Carlos III University of Madrid", 
          "id": "https://www.grid.ac/institutes/grid.7840.b", 
          "name": [
            "Computer Science Department, Universidad Carlos III de Madrid, Avda. de la Universidad 30, 28911, Leganes, Madrid, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Baldominos", 
        "givenName": "Alejandro", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Carlos III University of Madrid", 
          "id": "https://www.grid.ac/institutes/grid.7840.b", 
          "name": [
            "Computer Science Department, Universidad Carlos III de Madrid, Avda. de la Universidad 30, 28911, Leganes, Madrid, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Saez", 
        "givenName": "Yago", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Carlos III University of Madrid", 
          "id": "https://www.grid.ac/institutes/grid.7840.b", 
          "name": [
            "Computer Science Department, Universidad Carlos III de Madrid, Avda. de la Universidad 30, 28911, Leganes, Madrid, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Isasi", 
        "givenName": "Pedro", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1145/2834892.2834896", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1001211764"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2908812.2908890", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002672822"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1273496.1273556", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002982013"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s12065-007-0002-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003421528", 
          "https://doi.org/10.1007/s12065-007-0002-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s12065-007-0002-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003421528", 
          "https://doi.org/10.1007/s12065-007-0002-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/937503.937505", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1008740328"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11263-015-0816-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009767488", 
          "https://doi.org/10.1007/s11263-015-0816-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10462-011-9270-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010827521", 
          "https://doi.org/10.1007/s10462-011-9270-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3233/his-2007-4304", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1016284263"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pcbi.1002236", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017268549"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/323533a0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018367015", 
          "https://doi.org/10.1038/323533a0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bfb0029770", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019931233", 
          "https://doi.org/10.1007/bfb0029770"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3389/frobt.2016.00040", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021308176"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(91)90032-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022090648"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(91)90032-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022090648"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2576768.2598358", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022599118"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1108/eb005587", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022661580"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-32494-1_4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022688207", 
          "https://doi.org/10.1007/3-540-32494-1_4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf02551274", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1023250347", 
          "https://doi.org/10.1007/bf02551274"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf02551274", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1023250347", 
          "https://doi.org/10.1007/bf02551274"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1146/annurev.es.09.110178.000335", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024632576"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/artl.2009.15.2.15202", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025038480"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/b978-1-4832-1448-1.50014-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026046705"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/int.4550080406", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026534251"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/mind/lix.236.433", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027055246"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1276958.1277162", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1030329076"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/348027a0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032313221", 
          "https://doi.org/10.1038/348027a0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/106365602320169811", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033705757"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/s0893-6080(05)80061-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034883878"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/neco.1997.9.8.1735", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038140272"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(91)90033-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040786575"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(91)90033-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040786575"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1371/journal.pcbi.1002063", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1041794635"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/neco.1990.2.2.198", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042651472"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/artl_a_00071", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045403364"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(94)90023-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049597949"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(94)90023-x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049597949"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(91)90031-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049953486"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0893-6080(91)90031-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049953486"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bfb0029764", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050531071", 
          "https://doi.org/10.1007/bfb0029764"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf01931367", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051709453", 
          "https://doi.org/10.1007/bf01931367"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf01931367", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051709453", 
          "https://doi.org/10.1007/bf01931367"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-2789(90)90078-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052511580"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-2789(90)90078-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052511580"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1155/2013/425740", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052970499"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1162/neco.1989.1.1.151", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053187839"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/5.726791", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061179979"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/72.265960", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061218408"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/72.572107", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061218905"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cogann.1992.273949", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1086270344"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cogann.1992.273946", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1086275343"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cogann.1992.273950", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1086291318"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cogann.1992.273947", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1086302421"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cogann.1992.273942", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1086315705"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cogann.1992.273944", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1086350420"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/3071178.3071229", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090608637"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2016.90", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093359587"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/wacv.2015.71", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093567158"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/etd.1995.403479", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094570480"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/fskd.2016.7603153", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094965517"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cec.2003.1299414", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095366447"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/3067695.3076002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1096106561"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/3067695.3076002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1096106561"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2017.12.049", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100074591"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icip.2017.8297018", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101187463"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-77538-8_27", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1101372712", 
          "https://doi.org/10.1007/978-3-319-77538-8_27"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3390/s18041288", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1103624153"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-981-13-0200-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1104653782", 
          "https://doi.org/10.1007/978-981-13-0200-8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-99259-4_34", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1106254462", 
          "https://doi.org/10.1007/978-3-319-99259-4_34"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-99259-4_34", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1106254462", 
          "https://doi.org/10.1007/978-3-319-99259-4_34"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-030-00111-7_23", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1106429159", 
          "https://doi.org/10.1007/978-3-030-00111-7_23"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-030-00111-7_23", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1106429159", 
          "https://doi.org/10.1007/978-3-030-00111-7_23"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10710-018-9339-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1107273244", 
          "https://doi.org/10.1007/s10710-018-9339-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10710-018-9339-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1107273244", 
          "https://doi.org/10.1007/s10710-018-9339-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-030-03493-1_39", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1109832313", 
          "https://doi.org/10.1007/978-3-030-03493-1_39"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-030-03493-1_39", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1109832313", 
          "https://doi.org/10.1007/978-3-030-03493-1_39"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4899-7687-1_843", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1112905004", 
          "https://doi.org/10.1007/978-1-4899-7687-1_843"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-03-27", 
    "datePublishedReg": "2019-03-27", 
    "description": "Neuroevolution is the name given to a field of computer science that applies evolutionary computation for evolving some aspects of neural networks. After the AI Winter came to an end, neural networks reemerged to solve a great variety of problems. However, their usage requires designing their topology, a decision with a potentially high impact on performance. Whereas many works have tried to suggest rules-of-thumb for designing topologies, the truth is that there are not analytic procedures for determining the optimal one for a given problem, and trial-and-error is often used instead. Neuroevolution arose almost 3 decades ago, with some works focusing on the evolutionary design of the topology and most works describing techniques for learning connection weights. Since then, evolutionary computation has been proved to be a convenient approach for determining the topology and weights of neural networks, and neuroevolution has been applied to a great variety of fields. However, for more than 2 decades neuroevolution has mainly focused on simple artificial neural networks models, far from today\u2019s deep learning standards. This is insufficient for determining good architectures for modern networks extensively used nowadays, which involve multiple hidden layers, recurrent cells, etc. More importantly, deep and convolutional neural networks have become a de facto standard in representation learning for solving many different problems, and neuroevolution has only focused in this kind of networks in very recent years, with many works being presented in 2017 onward. In this paper, we review the field of neuroevolution during the last 3 decades. We will put the focus on very recent works on the evolution of deep and convolutional neural networks, which is a new but growing field of study. To the best of our knowledge, this is the best survey reviewing the literature in this field, and we have described the features of each work as well as their performance on well-known databases when available. This work aims to provide a complete reference of all works related to neuroevolution of convolutional neural networks up to the date. Finally, we will provide some future directions for the advancement of this research area.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s00521-019-04160-6", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1104357", 
        "issn": [
          "0941-0643", 
          "1433-3058"
        ], 
        "name": "Neural Computing and Applications", 
        "type": "Periodical"
      }
    ], 
    "name": "On the automated, evolutionary design of neural networks: past, present, and future", 
    "pagination": "1-27", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "3432cc8d245ea24c48b78e27359ad1cd7136b2db0e63fee5f3e72c8f5a114489"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00521-019-04160-6"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1113042666"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00521-019-04160-6", 
      "https://app.dimensions.ai/details/publication/pub.1113042666"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T13:17", 
    "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/v90/0000000368_0000000368/records_78934_00000001.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs00521-019-04160-6"
  }
]
 

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/s00521-019-04160-6'

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/s00521-019-04160-6'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00521-019-04160-6'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00521-019-04160-6'


 

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

275 TRIPLES      21 PREDICATES      88 URIs      16 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00521-019-04160-6 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N22b73b095d694acaae6f8937396975ce
4 schema:citation sg:pub.10.1007/3-540-32494-1_4
5 sg:pub.10.1007/978-1-4899-7687-1_843
6 sg:pub.10.1007/978-3-030-00111-7_23
7 sg:pub.10.1007/978-3-030-03493-1_39
8 sg:pub.10.1007/978-3-319-77538-8_27
9 sg:pub.10.1007/978-3-319-99259-4_34
10 sg:pub.10.1007/978-981-13-0200-8
11 sg:pub.10.1007/bf01931367
12 sg:pub.10.1007/bf02551274
13 sg:pub.10.1007/bfb0029764
14 sg:pub.10.1007/bfb0029770
15 sg:pub.10.1007/s10462-011-9270-6
16 sg:pub.10.1007/s10710-018-9339-y
17 sg:pub.10.1007/s11263-015-0816-y
18 sg:pub.10.1007/s12065-007-0002-4
19 sg:pub.10.1038/323533a0
20 sg:pub.10.1038/348027a0
21 https://doi.org/10.1002/int.4550080406
22 https://doi.org/10.1016/0167-2789(90)90078-4
23 https://doi.org/10.1016/0893-6080(91)90031-y
24 https://doi.org/10.1016/0893-6080(91)90032-z
25 https://doi.org/10.1016/0893-6080(91)90033-2
26 https://doi.org/10.1016/0893-6080(94)90023-x
27 https://doi.org/10.1016/b978-1-4832-1448-1.50014-7
28 https://doi.org/10.1016/j.neucom.2017.12.049
29 https://doi.org/10.1016/s0893-6080(05)80061-9
30 https://doi.org/10.1093/mind/lix.236.433
31 https://doi.org/10.1108/eb005587
32 https://doi.org/10.1109/5.726791
33 https://doi.org/10.1109/72.265960
34 https://doi.org/10.1109/72.572107
35 https://doi.org/10.1109/cec.2003.1299414
36 https://doi.org/10.1109/cogann.1992.273942
37 https://doi.org/10.1109/cogann.1992.273944
38 https://doi.org/10.1109/cogann.1992.273946
39 https://doi.org/10.1109/cogann.1992.273947
40 https://doi.org/10.1109/cogann.1992.273949
41 https://doi.org/10.1109/cogann.1992.273950
42 https://doi.org/10.1109/cvpr.2016.90
43 https://doi.org/10.1109/etd.1995.403479
44 https://doi.org/10.1109/fskd.2016.7603153
45 https://doi.org/10.1109/icip.2017.8297018
46 https://doi.org/10.1109/wacv.2015.71
47 https://doi.org/10.1145/1273496.1273556
48 https://doi.org/10.1145/1276958.1277162
49 https://doi.org/10.1145/2576768.2598358
50 https://doi.org/10.1145/2834892.2834896
51 https://doi.org/10.1145/2908812.2908890
52 https://doi.org/10.1145/3067695.3076002
53 https://doi.org/10.1145/3071178.3071229
54 https://doi.org/10.1145/937503.937505
55 https://doi.org/10.1146/annurev.es.09.110178.000335
56 https://doi.org/10.1155/2013/425740
57 https://doi.org/10.1162/106365602320169811
58 https://doi.org/10.1162/artl.2009.15.2.15202
59 https://doi.org/10.1162/artl_a_00071
60 https://doi.org/10.1162/neco.1989.1.1.151
61 https://doi.org/10.1162/neco.1990.2.2.198
62 https://doi.org/10.1162/neco.1997.9.8.1735
63 https://doi.org/10.1371/journal.pcbi.1002063
64 https://doi.org/10.1371/journal.pcbi.1002236
65 https://doi.org/10.3233/his-2007-4304
66 https://doi.org/10.3389/frobt.2016.00040
67 https://doi.org/10.3390/s18041288
68 schema:datePublished 2019-03-27
69 schema:datePublishedReg 2019-03-27
70 schema:description Neuroevolution is the name given to a field of computer science that applies evolutionary computation for evolving some aspects of neural networks. After the AI Winter came to an end, neural networks reemerged to solve a great variety of problems. However, their usage requires designing their topology, a decision with a potentially high impact on performance. Whereas many works have tried to suggest rules-of-thumb for designing topologies, the truth is that there are not analytic procedures for determining the optimal one for a given problem, and trial-and-error is often used instead. Neuroevolution arose almost 3 decades ago, with some works focusing on the evolutionary design of the topology and most works describing techniques for learning connection weights. Since then, evolutionary computation has been proved to be a convenient approach for determining the topology and weights of neural networks, and neuroevolution has been applied to a great variety of fields. However, for more than 2 decades neuroevolution has mainly focused on simple artificial neural networks models, far from today’s deep learning standards. This is insufficient for determining good architectures for modern networks extensively used nowadays, which involve multiple hidden layers, recurrent cells, etc. More importantly, deep and convolutional neural networks have become a de facto standard in representation learning for solving many different problems, and neuroevolution has only focused in this kind of networks in very recent years, with many works being presented in 2017 onward. In this paper, we review the field of neuroevolution during the last 3 decades. We will put the focus on very recent works on the evolution of deep and convolutional neural networks, which is a new but growing field of study. To the best of our knowledge, this is the best survey reviewing the literature in this field, and we have described the features of each work as well as their performance on well-known databases when available. This work aims to provide a complete reference of all works related to neuroevolution of convolutional neural networks up to the date. Finally, we will provide some future directions for the advancement of this research area.
71 schema:genre research_article
72 schema:inLanguage en
73 schema:isAccessibleForFree false
74 schema:isPartOf sg:journal.1104357
75 schema:name On the automated, evolutionary design of neural networks: past, present, and future
76 schema:pagination 1-27
77 schema:productId N34c69ace10a1447081bbb6b8c7730338
78 Ncb5c03e0d9e345739658d62bb15e135f
79 Nce35cd14c15246789a90b20de779e9e9
80 schema:sameAs https://app.dimensions.ai/details/publication/pub.1113042666
81 https://doi.org/10.1007/s00521-019-04160-6
82 schema:sdDatePublished 2019-04-11T13:17
83 schema:sdLicense https://scigraph.springernature.com/explorer/license/
84 schema:sdPublisher N6e3cdf1085664a2da5d1276ec6357518
85 schema:url https://link.springer.com/10.1007%2Fs00521-019-04160-6
86 sgo:license sg:explorer/license/
87 sgo:sdDataset articles
88 rdf:type schema:ScholarlyArticle
89 N18e60e17a939471793ffbe37c29ddcc8 schema:affiliation https://www.grid.ac/institutes/grid.7840.b
90 schema:familyName Isasi
91 schema:givenName Pedro
92 rdf:type schema:Person
93 N22b73b095d694acaae6f8937396975ce rdf:first N741ced1529bf48928c90c110c5db7a6f
94 rdf:rest Na61d49ef3c0848d8a7f6882ee772c928
95 N34c69ace10a1447081bbb6b8c7730338 schema:name dimensions_id
96 schema:value pub.1113042666
97 rdf:type schema:PropertyValue
98 N3815f87fb6474da9b8037c91b332f23a rdf:first N18e60e17a939471793ffbe37c29ddcc8
99 rdf:rest rdf:nil
100 N6e3cdf1085664a2da5d1276ec6357518 schema:name Springer Nature - SN SciGraph project
101 rdf:type schema:Organization
102 N741ced1529bf48928c90c110c5db7a6f schema:affiliation https://www.grid.ac/institutes/grid.7840.b
103 schema:familyName Baldominos
104 schema:givenName Alejandro
105 rdf:type schema:Person
106 Na61d49ef3c0848d8a7f6882ee772c928 rdf:first Nb72dea1d8b7646b094a673389063fec8
107 rdf:rest N3815f87fb6474da9b8037c91b332f23a
108 Nb72dea1d8b7646b094a673389063fec8 schema:affiliation https://www.grid.ac/institutes/grid.7840.b
109 schema:familyName Saez
110 schema:givenName Yago
111 rdf:type schema:Person
112 Ncb5c03e0d9e345739658d62bb15e135f schema:name doi
113 schema:value 10.1007/s00521-019-04160-6
114 rdf:type schema:PropertyValue
115 Nce35cd14c15246789a90b20de779e9e9 schema:name readcube_id
116 schema:value 3432cc8d245ea24c48b78e27359ad1cd7136b2db0e63fee5f3e72c8f5a114489
117 rdf:type schema:PropertyValue
118 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
119 schema:name Information and Computing Sciences
120 rdf:type schema:DefinedTerm
121 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
122 schema:name Artificial Intelligence and Image Processing
123 rdf:type schema:DefinedTerm
124 sg:journal.1104357 schema:issn 0941-0643
125 1433-3058
126 schema:name Neural Computing and Applications
127 rdf:type schema:Periodical
128 sg:pub.10.1007/3-540-32494-1_4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022688207
129 https://doi.org/10.1007/3-540-32494-1_4
130 rdf:type schema:CreativeWork
131 sg:pub.10.1007/978-1-4899-7687-1_843 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112905004
132 https://doi.org/10.1007/978-1-4899-7687-1_843
133 rdf:type schema:CreativeWork
134 sg:pub.10.1007/978-3-030-00111-7_23 schema:sameAs https://app.dimensions.ai/details/publication/pub.1106429159
135 https://doi.org/10.1007/978-3-030-00111-7_23
136 rdf:type schema:CreativeWork
137 sg:pub.10.1007/978-3-030-03493-1_39 schema:sameAs https://app.dimensions.ai/details/publication/pub.1109832313
138 https://doi.org/10.1007/978-3-030-03493-1_39
139 rdf:type schema:CreativeWork
140 sg:pub.10.1007/978-3-319-77538-8_27 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101372712
141 https://doi.org/10.1007/978-3-319-77538-8_27
142 rdf:type schema:CreativeWork
143 sg:pub.10.1007/978-3-319-99259-4_34 schema:sameAs https://app.dimensions.ai/details/publication/pub.1106254462
144 https://doi.org/10.1007/978-3-319-99259-4_34
145 rdf:type schema:CreativeWork
146 sg:pub.10.1007/978-981-13-0200-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1104653782
147 https://doi.org/10.1007/978-981-13-0200-8
148 rdf:type schema:CreativeWork
149 sg:pub.10.1007/bf01931367 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051709453
150 https://doi.org/10.1007/bf01931367
151 rdf:type schema:CreativeWork
152 sg:pub.10.1007/bf02551274 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023250347
153 https://doi.org/10.1007/bf02551274
154 rdf:type schema:CreativeWork
155 sg:pub.10.1007/bfb0029764 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050531071
156 https://doi.org/10.1007/bfb0029764
157 rdf:type schema:CreativeWork
158 sg:pub.10.1007/bfb0029770 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019931233
159 https://doi.org/10.1007/bfb0029770
160 rdf:type schema:CreativeWork
161 sg:pub.10.1007/s10462-011-9270-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010827521
162 https://doi.org/10.1007/s10462-011-9270-6
163 rdf:type schema:CreativeWork
164 sg:pub.10.1007/s10710-018-9339-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1107273244
165 https://doi.org/10.1007/s10710-018-9339-y
166 rdf:type schema:CreativeWork
167 sg:pub.10.1007/s11263-015-0816-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1009767488
168 https://doi.org/10.1007/s11263-015-0816-y
169 rdf:type schema:CreativeWork
170 sg:pub.10.1007/s12065-007-0002-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003421528
171 https://doi.org/10.1007/s12065-007-0002-4
172 rdf:type schema:CreativeWork
173 sg:pub.10.1038/323533a0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018367015
174 https://doi.org/10.1038/323533a0
175 rdf:type schema:CreativeWork
176 sg:pub.10.1038/348027a0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032313221
177 https://doi.org/10.1038/348027a0
178 rdf:type schema:CreativeWork
179 https://doi.org/10.1002/int.4550080406 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026534251
180 rdf:type schema:CreativeWork
181 https://doi.org/10.1016/0167-2789(90)90078-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052511580
182 rdf:type schema:CreativeWork
183 https://doi.org/10.1016/0893-6080(91)90031-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1049953486
184 rdf:type schema:CreativeWork
185 https://doi.org/10.1016/0893-6080(91)90032-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1022090648
186 rdf:type schema:CreativeWork
187 https://doi.org/10.1016/0893-6080(91)90033-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040786575
188 rdf:type schema:CreativeWork
189 https://doi.org/10.1016/0893-6080(94)90023-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1049597949
190 rdf:type schema:CreativeWork
191 https://doi.org/10.1016/b978-1-4832-1448-1.50014-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026046705
192 rdf:type schema:CreativeWork
193 https://doi.org/10.1016/j.neucom.2017.12.049 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100074591
194 rdf:type schema:CreativeWork
195 https://doi.org/10.1016/s0893-6080(05)80061-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034883878
196 rdf:type schema:CreativeWork
197 https://doi.org/10.1093/mind/lix.236.433 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027055246
198 rdf:type schema:CreativeWork
199 https://doi.org/10.1108/eb005587 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022661580
200 rdf:type schema:CreativeWork
201 https://doi.org/10.1109/5.726791 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061179979
202 rdf:type schema:CreativeWork
203 https://doi.org/10.1109/72.265960 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061218408
204 rdf:type schema:CreativeWork
205 https://doi.org/10.1109/72.572107 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061218905
206 rdf:type schema:CreativeWork
207 https://doi.org/10.1109/cec.2003.1299414 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095366447
208 rdf:type schema:CreativeWork
209 https://doi.org/10.1109/cogann.1992.273942 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086315705
210 rdf:type schema:CreativeWork
211 https://doi.org/10.1109/cogann.1992.273944 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086350420
212 rdf:type schema:CreativeWork
213 https://doi.org/10.1109/cogann.1992.273946 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086275343
214 rdf:type schema:CreativeWork
215 https://doi.org/10.1109/cogann.1992.273947 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086302421
216 rdf:type schema:CreativeWork
217 https://doi.org/10.1109/cogann.1992.273949 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086270344
218 rdf:type schema:CreativeWork
219 https://doi.org/10.1109/cogann.1992.273950 schema:sameAs https://app.dimensions.ai/details/publication/pub.1086291318
220 rdf:type schema:CreativeWork
221 https://doi.org/10.1109/cvpr.2016.90 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093359587
222 rdf:type schema:CreativeWork
223 https://doi.org/10.1109/etd.1995.403479 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094570480
224 rdf:type schema:CreativeWork
225 https://doi.org/10.1109/fskd.2016.7603153 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094965517
226 rdf:type schema:CreativeWork
227 https://doi.org/10.1109/icip.2017.8297018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101187463
228 rdf:type schema:CreativeWork
229 https://doi.org/10.1109/wacv.2015.71 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093567158
230 rdf:type schema:CreativeWork
231 https://doi.org/10.1145/1273496.1273556 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002982013
232 rdf:type schema:CreativeWork
233 https://doi.org/10.1145/1276958.1277162 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030329076
234 rdf:type schema:CreativeWork
235 https://doi.org/10.1145/2576768.2598358 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022599118
236 rdf:type schema:CreativeWork
237 https://doi.org/10.1145/2834892.2834896 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001211764
238 rdf:type schema:CreativeWork
239 https://doi.org/10.1145/2908812.2908890 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002672822
240 rdf:type schema:CreativeWork
241 https://doi.org/10.1145/3067695.3076002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1096106561
242 rdf:type schema:CreativeWork
243 https://doi.org/10.1145/3071178.3071229 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090608637
244 rdf:type schema:CreativeWork
245 https://doi.org/10.1145/937503.937505 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008740328
246 rdf:type schema:CreativeWork
247 https://doi.org/10.1146/annurev.es.09.110178.000335 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024632576
248 rdf:type schema:CreativeWork
249 https://doi.org/10.1155/2013/425740 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052970499
250 rdf:type schema:CreativeWork
251 https://doi.org/10.1162/106365602320169811 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033705757
252 rdf:type schema:CreativeWork
253 https://doi.org/10.1162/artl.2009.15.2.15202 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025038480
254 rdf:type schema:CreativeWork
255 https://doi.org/10.1162/artl_a_00071 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045403364
256 rdf:type schema:CreativeWork
257 https://doi.org/10.1162/neco.1989.1.1.151 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053187839
258 rdf:type schema:CreativeWork
259 https://doi.org/10.1162/neco.1990.2.2.198 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042651472
260 rdf:type schema:CreativeWork
261 https://doi.org/10.1162/neco.1997.9.8.1735 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038140272
262 rdf:type schema:CreativeWork
263 https://doi.org/10.1371/journal.pcbi.1002063 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041794635
264 rdf:type schema:CreativeWork
265 https://doi.org/10.1371/journal.pcbi.1002236 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017268549
266 rdf:type schema:CreativeWork
267 https://doi.org/10.3233/his-2007-4304 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016284263
268 rdf:type schema:CreativeWork
269 https://doi.org/10.3389/frobt.2016.00040 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021308176
270 rdf:type schema:CreativeWork
271 https://doi.org/10.3390/s18041288 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103624153
272 rdf:type schema:CreativeWork
273 https://www.grid.ac/institutes/grid.7840.b schema:alternateName Carlos III University of Madrid
274 schema:name Computer Science Department, Universidad Carlos III de Madrid, Avda. de la Universidad 30, 28911, Leganes, Madrid, Spain
275 rdf:type schema:Organization
 




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


...