Skip to main content
SpringerLink
Log in

Current-Mode Design of Sigmoid Activation Function Circuit

  • Short Paper
  • Published:
Circuits, Systems, and Signal Processing Aims and scope Submit manuscript

Abstract

This short paper presents a novel circuit for sigmoid activation function, which is based on the current-mode analog building block. The proposed circuit is simple, CMOS compatible, operates on current signals and provides an output voltage as desired activation function. The transition point in sigmoid function can be easily varied by changing the reference current. The proposed circuit is simulated using ± 1.75 V supply voltage. The proposal offers a promising advance for future neural applications.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

Data Availability

The paper has no associated data.

References:

  1. K. Al-Ruwaihi, CMOS analogue neurone circuit with programmable activation functions utilising mos transistors with optimised process/device parameters. IEE Proceed.-Circuits, Dev. Syst.. 144(6), 318–322 (1997)

    Article  Google Scholar 

  2. G. Khodabandehloo, M. Mirhassani, M. Ahmadi, Analog Implementation of a Novel Resistive-Type Sigmoidal Neuron. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 20, 750–754 (2012)

    Article  Google Scholar 

  3. S. Maheshwari, Electronic-Tuning-Facilitated Input Interface-Supported Load-Insensitive Filter with Extended Frequency Range. J. Circuits, Syst. Comput.. 30(7), 2150130 (2021)

    Article  Google Scholar 

  4. V. Massimo, M. Tatiana, S. Sebastiano et al., A low-voltage, low-power reconfigurable current-mode softmax circuit for analog neural networks. Electronics 10(9), 1004 (2021)

    Article  Google Scholar 

  5. C. Toumazou, F. J. Lidgey, D. G. Haigh, Analogue IC design: the current-mode approach, IET Press. (1998).

  6. S. Xu, X. Li, C. Xie, H. Chen et al., A High-Precision Implementation of the Sigmoid Activation Function for Computing-in-Memory Architecture. Micromachines. 12, 1183 (2021)

    Article  Google Scholar 

  7. S. Yang et al., Efficient hardware implementation of the subthalamic nucleus-external globus pallidus oscillation system and its dynamics investigation. Neural Netw. 94, 220–238 (2017)

    Article  Google Scholar 

Download references

Acknowledgements

The author thanks anonymous reviewers for very critical comments to improve the paper. The author also thanks the editorial board for recommending the paper.

Author information

Authors and Affiliations

  1. Department of Electronics Engineering, Aligarh Muslim University, Aligarh, India

    Sudhanshu Maheshwari

Authors
  1. Sudhanshu Maheshwari
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sudhanshu Maheshwari.

Ethics declarations

Conflict of interests

The author declares no conflict of interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Maheshwari, S. Current-Mode Design of Sigmoid Activation Function Circuit. Circuits Syst Signal Process 42, 6347–6354 (2023). https://doi.org/10.1007/s00034-023-02402-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00034-023-02402-6

Keywords

Search

Navigation