Skip to main content
Log in

Low-resource hardware implementation of the hyperbolic tangent for artificial neural networks

  • New applications of Artificial Neural Networks in Modeling & Control
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Artificial neural networks are a widespread tool with application in a variety of areas ranging from the social sciences to engineering. Many of these applications have reached a hardware implementation phase and have been documented in scientific papers. Unfortunately, most of the implementations have a simplified hyperbolic tangent replacement which has been the most common problem, as well as the most resource-consuming block in terms of hardware. This paper proposes a low-resource hardware implementation of the hyperbolic tangent, by using the simplest solution in order to obtain the lowest error possible thus far with a set of 25 polynomials of third order, obtained with Chebyshev interpolations. The results obtained show that the solution proposed holds a low error while simultaneously promising the use of low resources, as only third-order polynomials are used.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Dias FM, Antunes A, Mota A (2004) Artificial neural networks: a review of commercial hardware. Eng Appl Artif Intell 17:945–952

    Article  Google Scholar 

  2. Stieglitz T, Meyer J (2006) Biomedical microdevices for neural implants. BIOMEMS Microsyst 16:71–137

    Article  Google Scholar 

  3. Pinto JOP, Bose BK, Leite LC, Silva LEB, Romero ME (2006) Field programmable gate array (FPGA) based neural network implementation of stator flux oriented vector control of induction motor drive. In: IEEE international conference on industrial technology, pp 31–34

  4. Ferreira P, Ribeiro P, Antunes A, Morgado Dias F (2007) A high bit resolution FPGA implementation of a FNN with a new algorithm for the activation function. Neurocomputing 71:71–77

    Article  Google Scholar 

  5. Quarteroni A, Sacco R, Saleri F (2000) Numerical mathematics. Springer, Berlin

    Google Scholar 

  6. Recktenwald GW (2000) Numerical methods with matlab: implementations and applications. Prentice Hall, Englewood Cliffs, NJ

    Google Scholar 

  7. Gil A, Segura J, Temme NM (2007) Numerical methods for special functions. SIAM—Society for Industrial and Applied Mathematics, Philadelphia

    Book  MATH  Google Scholar 

  8. Mason JC, Handscomb DC (2003) Chebyshev polynomials, 2nd edn. Chapman and Hall-CRC, Press LLC, Boca Raton, FL

    MATH  Google Scholar 

  9. Quarteroni A, Saleri F, Gervasio P (2010) Scientific computing with MATLAB and octave, 3rd edn. Springer, Berlin

    Book  Google Scholar 

Download references

Acknowledgments

The authors would like to acknowledge the Portuguese Foundation for Science and Technology for their support in this work through the project PEst-OE/EEI/LA0009/2011.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Darío Baptista.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Baptista, D., Morgado-Dias, F. Low-resource hardware implementation of the hyperbolic tangent for artificial neural networks. Neural Comput & Applic 23, 601–607 (2013). https://doi.org/10.1007/s00521-013-1407-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-013-1407-x

Keywords

Navigation