Neural Networks and Deep Learning

  • Jürgen Franke
  • Wolfgang Karl Härdle
  • Christian Matthias Hafner
Part of the Universitext book series (UTX)


Deep learning is a group of optimisation methods for artificial neural networks. The field consists of three major branches.


  1. Abberger, K. (1997). Quantile smoothing in financial time series. Statistical Papers, 38, 125–148.MathSciNetCrossRefGoogle Scholar
  2. Anders, U. (1997). Statistische neuronale Netze. München: Vahlen.Google Scholar
  3. Back, A., & Tsoi, A.C. (1991). Fir and iir synapses, a new neural network architecture for time series modeling. Neural Computation, Massachusetts Institute of Technology, 3, 375–385.CrossRefGoogle Scholar
  4. Ben Taieb, S., Sorjamaa, A., & Bontempi, G. (2010). Multiple-output modeling for multi-step-ahead time series forecasting. Neurocomputing, 73(10–12), 1950–1957.CrossRefGoogle Scholar
  5. Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2), 157–166.CrossRefGoogle Scholar
  6. Bol, G., Nakhaeizadeh, G., & Vollmer, K.-H. (1996). Finanzmarktanalyse und -prognose mit innovativen quantitativen Verfahren. Heidelberg: Physica-Verlag.CrossRefGoogle Scholar
  7. Chen, S., Chen, C. Y.-H., Härdle, W. K., Lee, T., & Ong, B. (2017). Crix index: Analysis of a cryptocurrency index for portfolio investment. In D. Lee Kuo Chen, & R. Deng (Eds.), Handbook of digital finance and financial inclusion: Cryptocurrency, FinTech, InsurTech, Regulation, ChinaTech, Mobile Security, and Distributed Ledger. 1st Edition.Google Scholar
  8. Eisl, A., Gasser, S. M., & Weinmayer, K. (2015). Caveat emptor: Does Bitcoin improve portfolio diversification? SSRN Scholarly Paper ID 2408997. Rochester, NY: Social Science Research Network.Google Scholar
  9. Elendner, H., Trimborn, S., Ong, B., & Lee, T. M. (2018). The cross-section of cryptocurrencies as financial assets: Investing in crypto-currencies beyond bitcoin. In D. Lee Kuo Chen, & R. Deng (Eds.), Handbook of digital finance and financial inclusion: Cryptocurrency, FinTech, InsurTech, Regulation, ChinaTech, Mobile Security, and Distributed Ledger. 1st Edition.Google Scholar
  10. Elman, J. (1990). Finding structure in time. Cognitive Science, University of California, San Diego, 14, 179–211.Google Scholar
  11. Fan, J., & Yao, Q. (1998). Efficient estimation of conditional variance functions in stochastic regression. Biometrika, 85, 645–660.MathSciNetCrossRefGoogle Scholar
  12. Franke, J. (1999). Nonlinear and nonparametric methods for analyzing financial time series. In P. Kall, & H.-J. Luethi (Eds.), Operation research proceedings 98. Heidelberg: Springer-Verlag.Google Scholar
  13. Franke, J. (2000). Portfolio management and market risk quantification using neural networks. Statistics and finance: An interface. Imperial College Press: London.Google Scholar
  14. Franke, J., & Diagne, M. (2006). Estimating market risk with neural networks. Statistics and Decisions, 24, 233–253.MathSciNetzbMATHGoogle Scholar
  15. Franke, J., Kreiss, J., Mammen, E., & Neumann, M. (2003). Properties of the nonparametric autoregressive bootstrap. Journal of Time Series Analysis, 23, 555–585.MathSciNetCrossRefGoogle Scholar
  16. Franke, J., & Neumann, M. (2000). Bootstrapping neural networks. Neural Computation, 12, 1929–1949.CrossRefGoogle Scholar
  17. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.zbMATHGoogle Scholar
  18. Haykin, S. (1999). Neural networks: a comprehensive foundation. Prentice-Hall.zbMATHGoogle Scholar
  19. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, Massachusetts Institute of Technology, 9(8), 1735–1780.CrossRefGoogle Scholar
  20. Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2, 359–366.CrossRefGoogle Scholar
  21. Jordan, M. (1986). Serial order: A parallel distributed processing approach. Technical Report, Institute for Cognitive Science, University of California, San Diego, 8604.Google Scholar
  22. Koenker, R., & Bassett, G. (1978). Regression quantiles. Econometrica, 46, 33–50.MathSciNetCrossRefGoogle Scholar
  23. Müller, T., & Nietzer, H. (1993). Das große Buch der technischen Indikatoren. TM Börsenverlag.Google Scholar
  24. Murata, N., Yoskizawa, S., & Amari, S. (1994). Network information criterion - determining the number of hidden units for an artificial neural network model. IEEE Trans. Neural Networks, 5, 865–872.CrossRefGoogle Scholar
  25. Pascanu, R., Mikolov, T., & Bengio, Y. (2013). On the difficulty of training recurrent neural networks. In S. Dasgupta, & D. McAllester (Eds.), Proceedings of the 30th international conference on machine learning, Vol. 28(3) of Proceedings of machine learning research (pp. 1310–1318). Atlanta, Georgia, USA: PMLR.Google Scholar
  26. Refenes, A.-P. (1995a). Neural networks for pattern recognition. Clarendon Press.Google Scholar
  27. Refenes, A.-P. (1995b). Neural networks in the capital market. Wiley, New York.Google Scholar
  28. Rehkugler, H., & Zimmermann, H. G. (1994). Neuronale Netze in der Ökonomie. München: Vahlen.Google Scholar
  29. Ripley, B. (1996). Pattern recognition and neural networks. Cambridge: Cambridge University Press.CrossRefGoogle Scholar
  30. Rojas, R. (1996). Neural networks: A systemic introduction. Springer.CrossRefGoogle Scholar
  31. Rüeger, S., & Ossen, A. (1997). The metric structure of weightspace. Neural Processing Letters, 5, 63–72.Google Scholar
  32. Teräsvirta, T., Lin, C.-F., & Granger, C. (1993). Power of the neural network linearity test. Journal of Time Series analysis, 14, 209–220.CrossRefGoogle Scholar
  33. Trimborn, S., & Härdle, W. K. (2018). CRIX an Index for cryptocurrencies. Journal of Empirical Finance, 49, 107–122.CrossRefGoogle Scholar
  34. Trimborn, S., Li, M., & Härdle, W. (2019). Investing with cryptocurrencies - a liquidity constrained investment approach. Journal of Financial Econometrics (forthcoming)Google Scholar
  35. Waibel, A., Hanazawa, T., G., H., Shikano, K., & Lang, K. (1989). Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37(3), 328–339.Google Scholar
  36. Welcker, J. (1994). Technische Aktienanalyse. Zürich: Verlag Moderne Industrie.Google Scholar
  37. White, H. (1989a). An additional hidden unit test for neglected nonlinearities in multilayer feedforward networks. In Proceedings of the International Joint Conference on Neural Networks, Zürich, Washington DC.Google Scholar
  38. White, H. (1989b). Some asymptotic results for learning in single hidden-layer feedforward network models. Journal of the American Statistical Association, 84, 1008–1013.MathSciNetCrossRefGoogle Scholar
  39. White, H. (1990). Connectionist nonparametric regression: multilayer feedforward networks can learn arbitrary mappings. Neural Networks, 3, 535–550.CrossRefGoogle Scholar
  40. Williams, R., & Zipser, D. (1989). A learning algorithm for continually running fully recurrent neural networks. Neural Computation, Massachusetts Institute of Technology, 1, 270–280.CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Jürgen Franke
    • 1
  • Wolfgang Karl Härdle
    • 2
  • Christian Matthias Hafner
    • 3
  1. 1.Department of MathematicsTechnische Universität KaiserslauternKaiserslauternGermany
  2. 2.Ladislaus von Bortkiewicz Chair of StatisticsHumboldt-Universität BerlinBerlinGermany
  3. 3.Louvain Institute of Data Analysis and Modeling in Economics and StatisticsUCLouvainLouvain-la-NeuveBelgium

Personalised recommendations