Skip to main content

2021 | OriginalPaper | Buchkapitel

WILDA: Wide Learning of Diverse Architectures for Classification of Large Datasets

verfasst von : Rui P. Cardoso, Emma Hart, David Burth Kurka, Jeremy Pitt

Erschienen in: Applications of Evolutionary Computation

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

In order to address scalability issues, which can be a challenge for Deep Learning methods, we propose Wide Learning of Diverse Architectures—a model that scales horizontally rather than vertically, enabling distributed learning. We propose a distributed version of a quality-diversity evolutionary algorithm (MAP-Elites) to evolve an architecturally diverse ensemble of shallow networks, each of which extracts a feature vector from the data. These features then become the input to a single shallow network which is optimised using gradient descent to solve a classification task. The technique is shown to perform well on two benchmark classification problems (MNIST and CIFAR). Additional experiments provide insight into the role that diversity plays in contributing to the performance of the repertoire.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Fußnoten
1
With the exception of a handful of papers in the combinatorial optimisation domain, for example [21].
 
Literatur
1.
2.
Zurück zum Zitat Cully, A., Clune, J., Tarapore, D., Mouret, J.B.: Robots that can adapt like animals. Nature 521(7553), 503 (2015)CrossRef Cully, A., Clune, J., Tarapore, D., Mouret, J.B.: Robots that can adapt like animals. Nature 521(7553), 503 (2015)CrossRef
4.
Zurück zum Zitat Hart, E., Steyven, A.S.W., Paechter, B.: Evolution of a functionally diverse swarm via a novel decentralised quality-diversity algorithm. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’18, pp. 101–108. ACM, New York (2018) Hart, E., Steyven, A.S.W., Paechter, B.: Evolution of a functionally diverse swarm via a novel decentralised quality-diversity algorithm. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’18, pp. 101–108. ACM, New York (2018)
5.
Zurück zum Zitat He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016) He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
7.
Zurück zum Zitat Krizhevsky, A.: Learning Multiple Layers of Features from Tiny Images. University of Toronto, Science Dept, Technical report (2009) Krizhevsky, A.: Learning Multiple Layers of Features from Tiny Images. University of Toronto, Science Dept, Technical report (2009)
8.
Zurück zum Zitat LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE (1998) LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE (1998)
11.
Zurück zum Zitat Murphy, K.P.: Machine learning: a probabilistic perspective (2012) Murphy, K.P.: Machine learning: a probabilistic perspective (2012)
12.
Zurück zum Zitat Pandey, G., Dukkipati, A.: To go deep or wide in learning? (2014) Pandey, G., Dukkipati, A.: To go deep or wide in learning? (2014)
13.
Zurück zum Zitat Paszke, A., et al.: Automatic differentiation in PyTorch. In: Advances in Neural Information Processing Systems 32 (2019) Paszke, A., et al.: Automatic differentiation in PyTorch. In: Advances in Neural Information Processing Systems 32 (2019)
14.
Zurück zum Zitat Pugh, J.K., Soros, L.B., Stanley, K.O.: Quality diversity: a new frontier for evolutionary computation. Front. Robot. AI 3, 40 (2016)CrossRef Pugh, J.K., Soros, L.B., Stanley, K.O.: Quality diversity: a new frontier for evolutionary computation. Front. Robot. AI 3, 40 (2016)CrossRef
16.
Zurück zum Zitat Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. arXiv preprint arXiv:1906.02243 (2019) Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. arXiv preprint arXiv:​1906.​02243 (2019)
17.
Zurück zum Zitat Suganuma, M., Shirakawa, S., Nagao, T.: A genetic programming approach to designing convolutional neural network architectures. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 497–504 (2017) Suganuma, M., Shirakawa, S., Nagao, T.: A genetic programming approach to designing convolutional neural network architectures. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 497–504 (2017)
18.
Zurück zum Zitat Sun, Y., Xue, B., Zhang, M., Yen, G.G.: Automatically designing CNN architectures using genetic algorithm for image classification. arXivpreprint arXiv:1808.03818 (2018) Sun, Y., Xue, B., Zhang, M., Yen, G.G.: Automatically designing CNN architectures using genetic algorithm for image classification. arXivpreprint arXiv:​1808.​03818 (2018)
19.
Zurück zum Zitat Sun, Y., Xue, B., Zhang, M., Yen, G.G.: Automatically designing CNN architectures using genetic algorithm for image classification. arXiv preprint arXiv:1808.03818 (2018) Sun, Y., Xue, B., Zhang, M., Yen, G.G.: Automatically designing CNN architectures using genetic algorithm for image classification. arXiv preprint arXiv:​1808.​03818 (2018)
20.
Zurück zum Zitat Szerlip, P.A., Morse, G., Pugh, J.K., Stanley, K.O.: Unsupervised feature learning through divergent discriminative feature accumulation. In: Proceedings of the National Conference on Artificial Intelligence (2015) Szerlip, P.A., Morse, G., Pugh, J.K., Stanley, K.O.: Unsupervised feature learning through divergent discriminative feature accumulation. In: Proceedings of the National Conference on Artificial Intelligence (2015)
21.
Zurück zum Zitat Urquhart, N., Hart, E.: Optimisation and illumination of a real-world workforce scheduling and routing application (wsrp) via map-elites. In: International Conference on Parallel Problem Solving from Nature, pp. 488–499. Springer (2018) Urquhart, N., Hart, E.: Optimisation and illumination of a real-world workforce scheduling and routing application (wsrp) via map-elites. In: International Conference on Parallel Problem Solving from Nature, pp. 488–499. Springer (2018)
23.
Zurück zum Zitat Zagoruyko, S., Komodakis, N.: Wide residual networks (2016) Zagoruyko, S., Komodakis, N.: Wide residual networks (2016)
Metadaten
Titel
WILDA: Wide Learning of Diverse Architectures for Classification of Large Datasets
verfasst von
Rui P. Cardoso
Emma Hart
David Burth Kurka
Jeremy Pitt
Copyright-Jahr
2021
DOI
https://doi.org/10.1007/978-3-030-72699-7_41

Premium Partner