Preserving differential privacy in convolutional deep belief networks

NH Phan, X Wu, D Dou - Machine learning, 2017 - Springer
The remarkable development of deep learning in medicine and healthcare domain presents
obvious privacy issues, when deep neural networks are built on users' personal and highly …

A novel approximation methodology and its efficient vlsi implementation for the sigmoid function

Z Qin, Y Qiu, H Sun, Z Lu, Z Wang… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
In this brief, a novel approximation method and its optimized hardware implementation are
proposed for the sigmoid function used in Deep Neural Networks (DNNs). Based on …

Very high accuracy hyperbolic tangent function implementation in fpgas

Z Hajduk, GR Dec - IEEE Access, 2023 - ieeexplore.ieee.org
The paper presents in detail a relatively simple implementation method of the hyperbolic
tangent function, particularly targeted for FPGAs. The research goal of the proposed method …

Low-error digital hardware implementation of artificial neuron activation functions and their derivative

A Armato, L Fanucci, EP Scilingo, D De Rossi - Microprocessors and …, 2011 - Elsevier
In this paper we propose a low-error approximation of the sigmoid function and hyperbolic
tangent, which are mainly used to activate the artificial neuron, based on the piecewise …

[PDF][PDF] Hardware implementation of hyperbolic tangent and sigmoid activation functions

Z Hajduk - Bulletin of the Polish Academy of Sciences. Technical …, 2018 - bibliotekanauki.pl
This paper presents the high accuracy hardware implementation of the hyperbolic tangent
and sigmoid activation functions for artificial neural networks. A kind of a direct …

[PDF][PDF] Chebyshev polynomial approximation for activation sigmoid function

M Vlcek - Neural Network World, 2012 - nnw.cz
CHEBYSHEV POLYNOMIAL APPROXIMATION FOR ACTIVATION SIGMOID FUNCTION 1.
Introduction Page 1 CHEBYSHEV POLYNOMIAL APPROXIMATION FOR ACTIVATION …

AHEAD: Automatic holistic energy-aware design methodology for MLP neural network hardware generation in proactive BMI edge devices

NS Huang, YC Chen, JC Larsen, P Manoonpong - Energies, 2020 - mdpi.com
The prediction of a high-level cognitive function based on a proactive brain–machine
interface (BMI) control edge device is an emerging technology for improving the quality of …

Non‐linear activation function approximation using a REMEZ algorithm

SR Chiluveru, M Tripathy… - IET Circuits, Devices & …, 2021 - Wiley Online Library
Here a more accurate piecewise approximation (PWA) scheme for non‐linear activation
function is proposed. It utilizes a precision‐controlled recursive algorithm to predict a sub …

Controlled-accuracy approximation of nonlinear functions for soft computing applications: A high performance co-proccessor for intelligent embedded systems

I del Campo, J Echanobe, E Asua… - 2015 IEEE Symposium …, 2015 - ieeexplore.ieee.org
Intelligent embedded systems can be found everywhere in a variety of innovative
applications. The main challenge consists in developing small-size single-chip embedded …

[PDF][PDF] Mejora del diagnóstico médico de radiografías de tórax usando aprendizaje profundo con aumento gradual de iteraciones.

A Hernández-Trinidad, E Pérez Careta… - DYNA-Ingeniería e …, 2022 - academia.edu
La neumonía es una afección inflamatoria del pulmón que afecta a los alvéolos. El
diagnóstico se basa en los síntomas y en el examen físico. Las radiografías de tórax son …