Implementation of neural network with approximations functions

被引：0

作者：

Hnatiuc, M ^{[1
]}

Lamarque, G ^{[1
]}

机构：

[1] Tech Univ Gh Asachi Iasi, Iasi, Romania

来源：

SCS 2003: INTERNATIONAL SYMPOSIUM ON SIGNALS, CIRCUITS AND SYSTEMS, VOLS 1 AND 2, PROCEEDINGS | 2003年

关键词：

non-linear functions; gauss function; sigmoid function; neural network;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The purpose of this work is to simulate a neural network with non-linear activation functions. The non-linear functions are simulated in Microsoft Visual Studio C++ 6.0 to observe the precision and to implement on the programmable logic devices. This network is realized to accept very small input values. The multiplication between input values and weight values is realized with the add-logarithm and exponential functions. One approximates all the non-linear functions with linear functions using shift-add blocks.

引用

页码：553 / 556

页数：4

共 50 条

[1] Approximation of functions and their derivatives: A neural network implementation with applications
Nguyen-Thien, T
Tran-Cong, T
APPLIED MATHEMATICAL MODELLING, 1999, 23 (09) : 687 - 704
[2] High precision FPGA implementation of neural network activation functions
Ortega-Zamorano, Francisco
Jerez, Jose M.
Juarez, Gustavo
Perez, Jorge O.
Franco, Leonardo
2014 IEEE SYMPOSIUM ON INTELLIGENT EMBEDDED SYSTEMS (IES), 2014, : 55 - 60
[3] Artificial neural network approximation of special functions: design, analysis and implementation
Shah, Divya K.
Vyawahare, Vishwesh A.
Sadanand, Sangeeth
INTERNATIONAL JOURNAL OF DYNAMICS AND CONTROL, 2025, 13 (01) : 25 - 25
[4] Hardware implementation of neural network with Sigmoidal activation functions using CORDIC
Tiwari, Vipin
Khare, Nilay
MICROPROCESSORS AND MICROSYSTEMS, 2015, 39 (06) : 373 - 381
[5] CONSTRUCTIVE APPROXIMATIONS FOR NEURAL NETWORKS BY SIGMOIDAL FUNCTIONS
JONES, LK
PROCEEDINGS OF THE IEEE, 1990, 78 (10) : 1586 - 1589
[6] Towards Current-Mode Analog Implementation of Deep Neural Network Functions
Wang, Shihao
AL-Tamimi, Karama M.
Hammad, Issam
El-Sankary, Kamal
2022 20TH IEEE INTERREGIONAL NEWCAS CONFERENCE (NEWCAS), 2022, : 322 - 326
[7] Approximations by multivariate perturbed neural network operators
Anastassiou, George A.
ANALYSIS AND APPLICATIONS, 2017, 15 (03) : 413 - 432
[8] Implementation of High Speed Tangent Sigmoid Transfer Function Approximations for Artificial Neural Network Applications on FPGA
Koyuncu, Ismail
ADVANCES IN ELECTRICAL AND COMPUTER ENGINEERING, 2018, 18 (03) : 79 - 86
[9] Sigmoidal approximations of Heaviside functions in neural lattice models
Han, Xiaoying
Kloeden, Peter E.
JOURNAL OF DIFFERENTIAL EQUATIONS, 2020, 268 (09) : 5283 - 5300
[10] Enhancing Cloud Security through Efficient Polynomial Approximations for Homomorphic Evaluation of Neural Network Activation Functions
Pulido-Gaytani, Bernardo
Tchernykh, Andrei
Babenko, Mikhail
Cortes-Mendoza, Jorge M.
Gonzalez-Velez, Horacio
Avetisyan, Arutyun
2024 IEEE 24TH INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND INTERNET COMPUTING WORKSHOPS, CCGRIDW 2024, 2024, : 42 - 49

← 1 2 3 4 5 →