nach oben

Erschienen in:

2020 | OriginalPaper | Buchkapitel

Unsupervisedly Learned Representations – Should the Quest Be Over?

verfasst von : Daniel N. Nissani (Nissensohn)

Erschienen in: Machine Learning, Optimization, and Data Science

Verlag: Springer International Publishing

Einloggen

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

search-config

KI-gestützte Suche

Aus

Abstract

After four decades of research there still exists a Classification accuracy gap of about 20% between our best Unsupervisedly Learned Representations methods and the accuracy rates achieved by intelligent animals. It thus may well be that we are looking in the wrong direction. A possible solution to this puzzle is presented. We demonstrate that Reinforcement Learning can learn representations which achieve the same accuracy as that of animals. Our main modest contribution lies in the observations that: a. when applied to a real world environment Reinforcement Learning does not require labels, and thus may be legitimately considered as Unsupervised Learning, and b. in contrast, when Reinforcement Learning is applied in a simulated environment it does inherently require labels and should thus be generally be considered as Supervised Learning. The corollary of these observations is that further search for Unsupervised Learning competitive paradigms which may be trained in simulated environments may be futile.

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!

Jetzt informieren

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!

Jetzt informieren

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!

Jetzt informieren

Vorheriges Kapitel Heuristic Search in LegalTech: Dynamic Allocation of Legal Cases to Legal Staff

Nächstes Kapitel Bayesian Optimization with Local Search

See e.g. Yann LeCun Interview, IEEE Spectrum, Feb. 2015: “…The bottom line is that the brain is much better than our model at doing unsupervised learning…”.

So that, like Moses on Mount Nebo, we may be able to see Promised Land but will never reach it (Deuteronomy 34:4).

The reader may refer to https://stats.stackexchange.com/questions/243384/deriving-bellmans-equation-in-reinforcement-learning for a neat proof of the Bellman equation by Jie Shi.

Matlab code of this simple setup will be available upon request from the Author.

We could consider in principle the case wherein the Environment predicts by itself a label from the Dog’s photograph; this however requires the Environment to be a trained classifier, which enters us into an endless loop.

Arora, S., Bhaskara, A., Ge, R., Ma, T.: Provable bounds for learning some deep representations. In: ICML 2014 (2014)

Bengio, Y., et al.: Deep learners benefit more from out-of-distribution examples. In: AISTATS 2011 (2011)

Bengio, Y., Courville, A.: Representation learning: a review and new perspectives. arXiv:1206.5538 (2014)

Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: NIPS 2007 (2007)

Bengio, Y.: Deep Learning of Representations for Unsupervised and Transfer Learning, JMLR 2012

Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)

Coates, A., Lee, H., Ng, A.Y.: An analysis of single-layer networks in unsupervised feature learning. In: AISTATS 2011 (2011)

Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. arXiv:1505.05192 (2016)

Donahue, J., Krahenbuhl, P., Darrell, T.: Adversarial feature learning. arXiv;1605.09782 (2017)

Erhan, D., Bengio, Y., Courville, A., Manzagol, P., Vincent, P.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11, 625–660 (2010)MathSciNetMATH

Hessel, M.: Rainbow: combining improvements in deep reinforcement learning. In: AAAI 2018 (2018)

Hinton, G.E., Dayan, P., Frey, B.J., Neal, R.M.: The wake-sleep algorithm for unsupervised neural networks. Science 268(5214), 1158–1161 (1995)CrossRef

Larochelle, H., Bengio, Y., Louradour, J., Lamblin, P.: Exploring strategies for training deep neural networks. J. Mach. Learn. Res. 1, 1–40 (2009)MATH

Lowe, D.G.: Object recognition from local scale-invariant features. In: Proceedings of the International Conference on Computer Vision (1999)

Mesnil, G., et al.: Unsupervised and transfer learning challenge: a deep learning approach. In: JMLR 2011 (2011)

Noroozi, Mehdi, Favaro, Paolo: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, Bastian, Matas, Jiri, Sebe, Nicu, Welling, Max (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69–84. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_5CrossRef

Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583), 607–9 (1996)

Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T.: Context encoders: feature learning by inpainting. In: IEEE CVPR 2016 (2016)

Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial network. In: ICLR 2016 (2016)

Ranzato, M.A., Poultney, C., Chopra, S., LeCun, Y.: Efficient learning of sparse representations with an energy-based model. In: NIPS 2006 (2006)

Ranzato, M.A., Huang, F., Boureau, Y., LeCun, Y.: Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: IEEE CVPR 2007 (2007)

Rifai, S., Vincent, P., Muller, X., Glorot, X., Bengio, Y.: Contractive auto-encoders: explicit invariance during feature extraction. In: ICML 2011 (2011)

Russakovsky, Olga., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-yMathSciNetCrossRef

Salakhutdinov, R., Hinton, G.: Learning a nonlinear embedding by preserving class neighborhood structure. J. Machi. Learn. Res. (2007)

Sanger, T.D.: An optimality principle for unsupervised learning. In: NIPS 1988 (1988)

Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)

Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: NIPS 2000 (2000)

Tesauro, G.: TD-gammon, a self-teaching backgammon program, achieves master-level play. Neural Comput. 6, 215–219 (1994)CrossRef

Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. (2010)

Wang, X., Gupta, A.: Unsupervised learning of visual representations using videos. In: IEEE ICCV 2015 (2015)

Xie, S., Girshick, R., Dollar, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In; CVPR 2017 (2017)

Zhang, R., Isola, P., Efros, A.A.: Split-Brain autoencoders: unsupervised learning by cross-channel prediction. In: CVPR 2017 (2017)

Titel: Unsupervisedly Learned Representations – Should the Quest Be Over?
verfasst von: Daniel N. Nissani (Nissensohn)
Verlag: Springer International Publishing
Buch: Machine Learning, Optimization, and Data Science
Print ISBN: 978-3-030-64579-3

Electronic ISBN: 978-3-030-64580-9

Copyright-Jahr: 2020
DOI: https://doi.org/10.1007/978-3-030-64580-9_29

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

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

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner