Efficient Implementation of Activation Functions for LSTM accelerators

Page view(s)
92
Checked on Aug 10, 2025
Efficient Implementation of Activation Functions for LSTM accelerators
Title:
Efficient Implementation of Activation Functions for LSTM accelerators
Journal Title:
2021 IFIP/IEEE 29th International Conference on Very Large Scale Integration (VLSI-SoC)
Keywords:
Publication Date:
17 November 2021
Citation:
Chong, Y. S., Goh, W. L., Ong, Y. S., Nambiar, V. P., & Do, A. T. (2021). Efficient Implementation of Activation Functions for LSTM accelerators. 2021 IFIP/IEEE 29th International Conference on Very Large Scale Integration (VLSI-SoC). https://doi.org/10.1109/vlsi-soc53125.2021.9606971
Abstract:
Activation functions such as hyperbolic tangent (tanh) and logistic sigmoid (sigmoid) are critical computing elements in a long short term memory (LSTM) cell and network. These activation functions are non-linear, leading to challenges in their hardware implementations. Area-efficient and high performance hardware implementation of these activation functions thus becomes crucial to allow high throughput in a LSTM accelerator. In this work, we propose an approximation scheme which is suitable for both tanh and sigmoid functions. The proposed hardware for sigmoid function is 8.3 times smaller than the state-of-the-art, while for tanh function, it is the second smallest design. When applying the approximated tanh and sigmoid of 2% error in a LSTM cell computation, its final hidden state and cell state record errors of 3.1% and 5.8% respectively. When the same approximated functions are applied to a single layer LSTM network of 64 hidden nodes, the accuracy drops by 2.8% only. This proposed small yet accurate activation function hardware is promising to be used in Internet of Things (IoT) applications where accuracy can be traded off for ultra-low power consumption.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - Programmatic (RIE 2020, AME domain)
Grant Reference no. : A1687b0033
Description:
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2324-8440
Files uploaded: