Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Efficient Neural Networks on the Edge with FPGAs by Optimizing an Adaptive Activation Function

Version 1 : Received: 18 January 2024 / Approved: 19 January 2024 / Online: 19 January 2024 (06:11:51 CET)

A peer-reviewed article of this Preprint also exists.

Jiang, Y.; Vaicaitis, A.; Dooley, J.; Leeser, M. Efficient Neural Networks on the Edge with FPGAs by Optimizing an Adaptive Activation Function. Sensors 2024, 24, 1829. Jiang, Y.; Vaicaitis, A.; Dooley, J.; Leeser, M. Efficient Neural Networks on the Edge with FPGAs by Optimizing an Adaptive Activation Function. Sensors 2024, 24, 1829.

Abstract

The implementation of neural networks (NN) on edge devices enables local processing of wireless data but faces challenges such as high computational complexity and memory requirements when deep neural networks (DNN) are used. Shallow neural networks customized for specific problems are more efficient, requiring fewer resources, and resulting in a lower latency solution. An additional benefit of the smaller network size is that it is suitable for real-time processing on edge devices. The main concern with shallow neural networks is their accuracy performance compared to DNNs. In this paper, we demonstrate that a customized adaptive activation function (AAF) can meet the accuracy of a DNN. We designed an efficient FPGA implementation for a customized segmented spline curve neural network (SSCNN) structure to replace the traditional fixed activation function with an AAF. We compared our SSCNN with different neural network structures such as real-valued time delay neural network (RVTDNN), augmented real-valued time delay neural network (ARVTDNN), and deep neural networks with different parameters. Our proposed SSCNN implementation uses 40% fewer hardware resources and no Block RAMS compared to the DNN with similar accuracy. We experimentally validate this computationally efficient and memory-saving FPGA implementation of SSCNN for digital predistortion of RF power amplifiers using the AMD/Xilinx RFSoC ZCU111. The implemented solution uses less than 3% of the available resources. The solution also enables an increase of the clock frequency to 221.12 MHz, allowing the transmission of wide bandwidth signals.

Keywords

Adaptive Activation Function (AAF); Neural Network; FPGA; Deep Learning; Digital Predistortion

Subject

Engineering, Electrical and Electronic Engineering

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.