Abstract
Deep learning is one of the fastest growing areas of machine learning and a hot topic in both academia and industry. This tutorial tries to figure out what are the real mechanisms that make this technique a breakthrough with respect to the past. To this end, we will review what is a neural network, how we can learn its parameters by using observational data, some of the most common architectures (CNN, LSTM, etc.) and some of the tricks that have been developed during the last years.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The number of weights we must learn for a \((M \times N)\) convolution kernel is only \((M \times N)\), which is independent of the size of the image.
- 2.
The computation of useful vectors for words is out of the scope of this tutorial, but the most common method is word embedding, an unsupervised method that is based on shallow neural networks.
References
Hebb, D.O.: The Organization of Behavior. Wiley & Sons, New York (1949)
Rosenblatt, F.: the perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65(6), 386–408 (1958). Cornell Aeronautical Laboratory
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Proceedings of the 25th International Conference on Neural Information Processing Systems (NIPS 2012), pp. 1097–1105. Curran Associates Inc., USA (2012)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-2010), pp. 807–814 (2010)
Csáji, B.C.: Approximation with Artificial Neural Networks, vol. 24, p. 48. Faculty of Sciences, Etvs Lornd University, Hungary (2001)
Sutton, R.S.: Two problems with backpropagation and other steepest-descent learning procedures for networks. In: Proceedings of 8th Annual Conference Cognitive Science Society (1986)
Duchi, J., Hazan, E., Singer, Y.: Adaptive Subgradient Methods for Online Learning and Stochastic Optimization. J. Mach. Learn. Res. 12, 2121–2159 (2011)
Kingma, D., Jimmy B.A.: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Bottou, L.: Online Algorithms and Stochastic Approximations. Online Learning and Neural Networks. Cambridge University Press, Cambridge (1998)
Mozer, M.C.: A focused backpropagation algorithm for temporal pattern recognition. In: Chauvin, Y., Rumelhart, D. Backpropagation: Theory, Architectures, and Applications, pp. 137–169. ResearchGate, Lawrence Erlbaum Associates, Hillsdale (1995). Accessed 21 Aug 2017
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling arXiv:1412.3555 (2014)
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D.G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: a system for large-scale machine learning. In: OSDI, vol. 16, pp. 265–283 (2016)
Paszke, A., Gross, S., Chintala, S.: PyTorch. GitHub repository (2017). https://github.com/orgs/pytorch/people
Chollet, F.: (2017). Keras (2015). http://keras.io
Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep learning, vol. 1. MIT press, Cambridge (2016)
Nielsen, M.A.: Neural Networks and Deep Learning. Determination Press (2015)
Acknowledgement
This work was partially supported by TIN2015-66951-C2 and SGR 1219 grants. I thank the anonymous reviewers for their careful reading of the manuscript and their many insightful comments and suggestions. I also want to acknowledge the support of NVIDIA Corporation with the donation of a Titan X Pascal GPU. Finally, I would like to express my sincere appreciation to the organizers of the Seventh European Business Intelligence & Big Data Summer School.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Vitrià, J. (2018). Let’s Open the Black Box of Deep Learning!. In: Zimányi, E. (eds) Business Intelligence and Big Data. eBISS 2017. Lecture Notes in Business Information Processing, vol 324. Springer, Cham. https://doi.org/10.1007/978-3-319-96655-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-96655-7_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-96654-0
Online ISBN: 978-3-319-96655-7
eBook Packages: Computer ScienceComputer Science (R0)