Skip to main content

2020 | OriginalPaper | Buchkapitel

Deep Convolutional Gaussian Processes

verfasst von : Kenneth Blomqvist, Samuel Kaski, Markus Heinonen

Erschienen in: Machine Learning and Knowledge Discovery in Databases

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

We propose deep convolutional Gaussian processes, a deep Gaussian process architecture with convolutional structure. The model is a principled Bayesian framework for detecting hierarchical combinations of local features for image classification. We demonstrate greatly improved image classification performance compared to current convolutional Gaussian process approaches on the MNIST and CIFAR-10 datasets. In particular, we improve state-of-the-art CIFAR-10 accuracy by over 10% points.

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
We note that after placing our current manuscript in arXiv in October 2018, a subsequent arXiv manuscript has already extended the proposed deep convolution model by introducing location-dependent kernel [6].
 
Literatur
1.
Zurück zum Zitat Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: OSDI, vol. 16, pp. 265–283 (2016) Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: OSDI, vol. 16, pp. 265–283 (2016)
2.
Zurück zum Zitat Blei, D.M., Kucukelbir, A., McAuliffe, J.D.: Variational inference: a review for statisticians. J. Am. Stat. Assoc. 112(518), 859–877 (2017)MathSciNetCrossRef Blei, D.M., Kucukelbir, A., McAuliffe, J.D.: Variational inference: a review for statisticians. J. Am. Stat. Assoc. 112(518), 859–877 (2017)MathSciNetCrossRef
3.
Zurück zum Zitat Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural networks. In: International Conference on Machine Learning, pp. 1613–1622 (2015) Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural networks. In: International Conference on Machine Learning, pp. 1613–1622 (2015)
4.
Zurück zum Zitat Chen, T., Fox, E., Guestrin, C.: Stochastic gradient Hamiltonian Monte Carlo. In: International Conference on Machine Learning, pp. 1683–1691 (2014) Chen, T., Fox, E., Guestrin, C.: Stochastic gradient Hamiltonian Monte Carlo. In: International Conference on Machine Learning, pp. 1683–1691 (2014)
5.
Zurück zum Zitat Damianou, A., Lawrence, N.: Deep Gaussian processes. In: AISTATS. PMLR, vol. 31, pp. 207–215 (2013) Damianou, A., Lawrence, N.: Deep Gaussian processes. In: AISTATS. PMLR, vol. 31, pp. 207–215 (2013)
6.
Zurück zum Zitat Dutordoir, V., van der Wilk, M., Artemev, A., Tomczak, M., Hensman, J.: Translation insensitivity for deep convolutional Gaussian processes. arXiv:1902.05888 (2019) Dutordoir, V., van der Wilk, M., Artemev, A., Tomczak, M., Hensman, J.: Translation insensitivity for deep convolutional Gaussian processes. arXiv:​1902.​05888 (2019)
7.
Zurück zum Zitat Duvenaud, D., Rippel, O., Adams, R., Ghahramani, Z.: Avoiding pathologies in very deep networks. In: AISTATS. PMLR, vol. 33, pp. 202–210 (2014) Duvenaud, D., Rippel, O., Adams, R., Ghahramani, Z.: Avoiding pathologies in very deep networks. In: AISTATS. PMLR, vol. 33, pp. 202–210 (2014)
8.
Zurück zum Zitat Duvenaud, D.K., Nickisch, H., Rasmussen, C.E.: Additive Gaussian processes. In: Advances in Neural Information Processing Systems, pp. 226–234 (2011) Duvenaud, D.K., Nickisch, H., Rasmussen, C.E.: Additive Gaussian processes. In: Advances in Neural Information Processing Systems, pp. 226–234 (2011)
9.
Zurück zum Zitat Evans, T.W., Nair, P.B.: Scalable Gaussian processes with grid-structured eigenfunctions (GP-GRIEF). In: International Conference on Machine Learning (2018) Evans, T.W., Nair, P.B.: Scalable Gaussian processes with grid-structured eigenfunctions (GP-GRIEF). In: International Conference on Machine Learning (2018)
10.
Zurück zum Zitat Garriga-Alonso, A., Aitchison, L., Rasmussen, C.E.: Deep convolutional networks as shallow Gaussian processes. In: ICLR (2019) Garriga-Alonso, A., Aitchison, L., Rasmussen, C.E.: Deep convolutional networks as shallow Gaussian processes. In: ICLR (2019)
11.
Zurück zum Zitat Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning, vol. 1. MIT Press, Cambridge (2016)MATH Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning, vol. 1. MIT Press, Cambridge (2016)MATH
12.
Zurück zum Zitat Havasi, M., Lobato, J.M.H., Fuentes, J.J.M.: Inference in deep Gaussian processes using stochastic gradient Hamiltonian Monte Carlo. In: NIPS (2018) Havasi, M., Lobato, J.M.H., Fuentes, J.J.M.: Inference in deep Gaussian processes using stochastic gradient Hamiltonian Monte Carlo. In: NIPS (2018)
13.
Zurück zum Zitat Hensman, J., Matthews, A., Ghahramani, Z.: Scalable variational Gaussian process classification. In: AISTATS. PMLR, vol. 38, pp. 351–360 (2015) Hensman, J., Matthews, A., Ghahramani, Z.: Scalable variational Gaussian process classification. In: AISTATS. PMLR, vol. 38, pp. 351–360 (2015)
14.
Zurück zum Zitat Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, vol. 1, p. 3 (2017) Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, vol. 1, p. 3 (2017)
15.
Zurück zum Zitat Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: ICLR (2014) Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: ICLR (2014)
16.
Zurück zum Zitat Krauth, K., Bonilla, E.V., Cutajar, K., Filippone, M.: AutoGP: exploring the capabilities and limitations of Gaussian process models. In: Uncertainty in Artificial Intelligence (2017) Krauth, K., Bonilla, E.V., Cutajar, K., Filippone, M.: AutoGP: exploring the capabilities and limitations of Gaussian process models. In: Uncertainty in Artificial Intelligence (2017)
17.
Zurück zum Zitat Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009) Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)
18.
Zurück zum Zitat Kumar, V., Singh, V., Srijith, P., Damianou, A.: Deep Gaussian processes with convolutional kernels. arXiv preprint arXiv:1806.01655 (2018) Kumar, V., Singh, V., Srijith, P., Damianou, A.: Deep Gaussian processes with convolutional kernels. arXiv preprint arXiv:​1806.​01655 (2018)
19.
Zurück zum Zitat Lee, J., Bahri, Y., Novak, R., Schoenholz, S.S., Pennington, J., Sohl-Dickstein, J.: Deep neural networks as Gaussian processes. In: ICLR (2018) Lee, J., Bahri, Y., Novak, R., Schoenholz, S.S., Pennington, J., Sohl-Dickstein, J.: Deep neural networks as Gaussian processes. In: ICLR (2018)
20.
Zurück zum Zitat MacKay, D.J.: A practical Bayesian framework for backpropagation networks. Neural Comput. 4, 448–472 (1992)CrossRef MacKay, D.J.: A practical Bayesian framework for backpropagation networks. Neural Comput. 4, 448–472 (1992)CrossRef
21.
Zurück zum Zitat Mallat, S.: Understanding deep convolutional networks. Phil. Trans. R. Soc. A 374(2065), 20150203 (2016)CrossRef Mallat, S.: Understanding deep convolutional networks. Phil. Trans. R. Soc. A 374(2065), 20150203 (2016)CrossRef
22.
Zurück zum Zitat Matthews, A.G.d.G., et al.: GPflow: a Gaussian process library using TensorFlow. J. Mach. Learn. Res. 18, 1–6 (2017) Matthews, A.G.d.G., et al.: GPflow: a Gaussian process library using TensorFlow. J. Mach. Learn. Res. 18, 1–6 (2017)
23.
Zurück zum Zitat McInnes, L., Healy, J.: UMAP: uniform manifold approximation and projection for dimension reduction. ArXiv e-prints, February 2018 McInnes, L., Healy, J.: UMAP: uniform manifold approximation and projection for dimension reduction. ArXiv e-prints, February 2018
25.
Zurück zum Zitat Rasmussen, C.E., Williams, C.K.: Gaussian Process for Machine Learning. MIT Press, Cambridge (2006)MATH Rasmussen, C.E., Williams, C.K.: Gaussian Process for Machine Learning. MIT Press, Cambridge (2006)MATH
26.
Zurück zum Zitat Remes, S., Heinonen, M., Kaski, S.: Non-stationary spectral kernels. In: Advances in Neural Information Processing Systems, pp. 4642–4651 (2017) Remes, S., Heinonen, M., Kaski, S.: Non-stationary spectral kernels. In: Advances in Neural Information Processing Systems, pp. 4642–4651 (2017)
27.
Zurück zum Zitat Salimbeni, H., Deisenroth, M.: Doubly stochastic variational inference for deep Gaussian processes. In: Advances in Neural Information Processing Systems, pp. 4588–4599 (2017) Salimbeni, H., Deisenroth, M.: Doubly stochastic variational inference for deep Gaussian processes. In: Advances in Neural Information Processing Systems, pp. 4588–4599 (2017)
28.
Zurück zum Zitat Snelson, E., Ghahramani, Z.: Sparse Gaussian processes using pseudo-inputs. In: Advances in Neural Information Processing Systems, pp. 1257–1264 (2006) Snelson, E., Ghahramani, Z.: Sparse Gaussian processes using pseudo-inputs. In: Advances in Neural Information Processing Systems, pp. 1257–1264 (2006)
29.
Zurück zum Zitat Springerberg, J., Klein, A., Falkner, S., Hutter, F.: Bayesian optimization with robust Bayesian neural networks. In: Advances in Neural Information Processing Systems, pp. 4134–4142 (2016) Springerberg, J., Klein, A., Falkner, S., Hutter, F.: Bayesian optimization with robust Bayesian neural networks. In: Advances in Neural Information Processing Systems, pp. 4134–4142 (2016)
30.
Zurück zum Zitat Sun, S., Zhang, G., Wang, C., Zeng, W., Li, J., Grosse, R.: Differentiable compositional kernel learning for Gaussian processes. In: ICML. PMLR, vol. 80 (2018) Sun, S., Zhang, G., Wang, C., Zeng, W., Li, J., Grosse, R.: Differentiable compositional kernel learning for Gaussian processes. In: ICML. PMLR, vol. 80 (2018)
31.
Zurück zum Zitat Tran, G.L., Bonilla, E.V., Cunningham, J.P., Michiardi, P., Filippone, M.: Calibrating deep convolutional Gaussian processes. In: AISTATS. PMLR, vol. 89, pp. 1554–1563 (2019) Tran, G.L., Bonilla, E.V., Cunningham, J.P., Michiardi, P., Filippone, M.: Calibrating deep convolutional Gaussian processes. In: AISTATS. PMLR, vol. 89, pp. 1554–1563 (2019)
32.
Zurück zum Zitat Wei, G., Tanner, M.: A Monte Carlo implementation of the EM algorithm and the poor mans data augmentation algorithms. J. Am. Stat. Assoc. 85, 699–704 (1990)CrossRef Wei, G., Tanner, M.: A Monte Carlo implementation of the EM algorithm and the poor mans data augmentation algorithms. J. Am. Stat. Assoc. 85, 699–704 (1990)CrossRef
33.
Zurück zum Zitat Van der Wilk, M., Rasmussen, C.E., Hensman, J.: Convolutional Gaussian processes. In: Advances in Neural Information Processing Systems, pp. 2849–2858 (2017) Van der Wilk, M., Rasmussen, C.E., Hensman, J.: Convolutional Gaussian processes. In: Advances in Neural Information Processing Systems, pp. 2849–2858 (2017)
34.
Zurück zum Zitat Williams, C.K.: Computing with infinite networks. In: Advances in Neural Information Processing Systems, pp. 295–301 (1997) Williams, C.K.: Computing with infinite networks. In: Advances in Neural Information Processing Systems, pp. 295–301 (1997)
35.
Zurück zum Zitat Wilson, A., Gilboa, E., Nehorai, A., Cunningham, J.: Fast multidimensional pattern extrapolation with Gaussian processes. In: AISTATS. PMLR, vol. 31 (2013) Wilson, A., Gilboa, E., Nehorai, A., Cunningham, J.: Fast multidimensional pattern extrapolation with Gaussian processes. In: AISTATS. PMLR, vol. 31 (2013)
36.
Zurück zum Zitat Wilson, A., Nickisch, H.: Kernel interpolation for scalable structured Gaussian processes (KISS-GP). In: International Conference on Machine Learning. PMLR, vol. 37, pp. 1775–1784 (2015) Wilson, A., Nickisch, H.: Kernel interpolation for scalable structured Gaussian processes (KISS-GP). In: International Conference on Machine Learning. PMLR, vol. 37, pp. 1775–1784 (2015)
37.
Zurück zum Zitat Wilson, A.G., Hu, Z., Salakhutdinov, R.R., Xing, E.P.: Stochastic variational deep kernel learning. In: Advances in Neural Information Processing Systems, pp. 2586–2594 (2016) Wilson, A.G., Hu, Z., Salakhutdinov, R.R., Xing, E.P.: Stochastic variational deep kernel learning. In: Advances in Neural Information Processing Systems, pp. 2586–2594 (2016)
38.
Zurück zum Zitat Wilson, A.G., Hu, Z., Salakhutdinov, R., Xing, E.P.: Deep kernel learning. In: AISTATS. PMLR, vol. 51, pp. 370–378 (2016) Wilson, A.G., Hu, Z., Salakhutdinov, R., Xing, E.P.: Deep kernel learning. In: AISTATS. PMLR, vol. 51, pp. 370–378 (2016)
Metadaten
Titel
Deep Convolutional Gaussian Processes
verfasst von
Kenneth Blomqvist
Samuel Kaski
Markus Heinonen
Copyright-Jahr
2020
DOI
https://doi.org/10.1007/978-3-030-46147-8_35