Optimizing Neural Networks with Learnable Non-Linear Activation Functions via Lookup-Based FPGA Acceleration

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yin, Mengyuan, Choong, Benjamin Chen Ming, Qu, Chuping, Goh, Rick Siow Mong, Wong, Weng-Fai, Luo, Tao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915460092526592
author Yin, Mengyuan
Choong, Benjamin Chen Ming
Qu, Chuping
Goh, Rick Siow Mong
Wong, Weng-Fai
Luo, Tao
author_facet Yin, Mengyuan
Choong, Benjamin Chen Ming
Qu, Chuping
Goh, Rick Siow Mong
Wong, Weng-Fai
Luo, Tao
contents Learned activation functions in models like Kolmogorov-Arnold Networks (KANs) outperform fixed-activation architectures in terms of accuracy and interpretability; however, their computational complexity poses critical challenges for energy-constrained edge AI deployments. Conventional CPUs/GPUs incur prohibitive latency and power costs when evaluating higher order activations, limiting deployability under ultra-tight energy budgets. We address this via a reconfigurable lookup architecture with edge FPGAs. By coupling fine-grained quantization with adaptive lookup tables, our design minimizes energy-intensive arithmetic operations while preserving activation fidelity. FPGA reconfigurability enables dynamic hardware specialization for learned functions, a key advantage for edge systems that require post-deployment adaptability. Evaluations using KANs - where unique activation functions play a critical role - demonstrate that our FPGA-based design achieves superior computational speed and over $10^4$ times higher energy efficiency compared to edge CPUs and GPUs, while maintaining matching accuracy and minimal footprint overhead. This breakthrough positions our approach as a practical enabler for energy-critical edge AI, where computational intensity and power constraints traditionally preclude the use of adaptive activation networks.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17069
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimizing Neural Networks with Learnable Non-Linear Activation Functions via Lookup-Based FPGA Acceleration
Yin, Mengyuan
Choong, Benjamin Chen Ming
Qu, Chuping
Goh, Rick Siow Mong
Wong, Weng-Fai
Luo, Tao
Hardware Architecture
Artificial Intelligence
Learned activation functions in models like Kolmogorov-Arnold Networks (KANs) outperform fixed-activation architectures in terms of accuracy and interpretability; however, their computational complexity poses critical challenges for energy-constrained edge AI deployments. Conventional CPUs/GPUs incur prohibitive latency and power costs when evaluating higher order activations, limiting deployability under ultra-tight energy budgets. We address this via a reconfigurable lookup architecture with edge FPGAs. By coupling fine-grained quantization with adaptive lookup tables, our design minimizes energy-intensive arithmetic operations while preserving activation fidelity. FPGA reconfigurability enables dynamic hardware specialization for learned functions, a key advantage for edge systems that require post-deployment adaptability. Evaluations using KANs - where unique activation functions play a critical role - demonstrate that our FPGA-based design achieves superior computational speed and over $10^4$ times higher energy efficiency compared to edge CPUs and GPUs, while maintaining matching accuracy and minimal footprint overhead. This breakthrough positions our approach as a practical enabler for energy-critical edge AI, where computational intensity and power constraints traditionally preclude the use of adaptive activation networks.
title Optimizing Neural Networks with Learnable Non-Linear Activation Functions via Lookup-Based FPGA Acceleration
topic Hardware Architecture
Artificial Intelligence
url https://arxiv.org/abs/2508.17069