Efficient Estimation of Sigmoid and Tanh Activation Functions for Homomorphically Encrypted Data Using Artificial Neural Networks
Year: 2024
Type: conference-paper
Abstract: This paper presents a novel approach to estimating Sigmoid and Tanh activation functions using Artificial Neural Networks (ANN) optimized for homomorphic encryption. The proposed method is compared against second-degree polynomial and Piecewise Linear approximations, demonstrating a minor loss in accuracy while maintaining computational efficiency. Our results suggest that the ANN-based estimator is a viable alternative for secure machine learning models requiring privacypreserving computation.
Authors: Mhd Raja Abou Harb, Baris Celiktas
Institution: Işık University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4406728329