Nonlinear Activation Functions for Artificial Neural Networks Realized in Hardware

被引：0

作者：

Dlugosz, Zofia ^{[1
]}

Dlugosz, Rafal ^{[2
,3
]}

机构：

[1] Poznan Univ Tech, Fac Comp, Ul Piotrowo 3A, Poznan, Poland

[2] UTP Univ Sci & Technol, Fac Telecommun Comp Sci & Elect, Ul Kaliskiego 7, PL-85796 Bydgoszcz, Poland

[3] Apt Poland SA, Ul Podgorki Tynieckie 2, PL-30399 Krakow, Poland

来源：

PROCEEDINGS OF THE 25TH INTERNATIONAL CONFERENCE MIXED DESIGN OF INTEGRATED CIRCUITS AND SYSTEM (MIXDES 2018) | 2018年

关键词：

Wavelet Neural Network; Fuzzy Neural Network; Hardware implementation; Approximation of activation function;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The paper presents a hardware efficient implementation of selected nonlinear activation functions of the neuron for the application in various artificial neural networks, including wavelet neural network (WNNs). Similar solutions may also be used in fuzzy neural networks. A software implementation of the activation function is relatively simple, however in hardware the realization is more complex. For this reason, we performed investigations, in which the training process was completed with simplified activation function. The comparison with the results obtained for an ideal function have shown that such a simplification is acceptable. The realized WNN has been successfully verified with selected signals composed of trigonometric functions, accompanied by the Gaussian noise.

引用

页码：381 / 384

页数：4

共 50 条

[1] A Comparison of Activation Functions in Artificial Neural Networks
Bircanoglu, Cenk
Arica, Nafiz
2018 26TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2018,
[2] Tunable Nonlinear Activation Functions for Optical Neural Networks
Williamson, Ian A. D.
Hughes, Tyler W.
Minkov, Momchil
Bartlett, Ben
Pai, Sunil
Fan, Shanhui
2020 CONFERENCE ON LASERS AND ELECTRO-OPTICS (CLEO), 2020,
[3] Universal Approximation of Nonlinear System Predictions in Sigmoid Activation Functions Using Artificial Neural Networks
Murugadoss, R.
Ramakrishnan, M.
2014 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND COMPUTING RESEARCH (IEEE ICCIC), 2014, : 1062 - 1067
[4] Artificial neural networks with adaptive multidimensional spline activation functions
Solazzi, M
Uncini, A
IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL III, 2000, : 471 - 476
[5] Fractional activation functions in feed-forward artificial neural networks
Ivanov, Alexander
2018 20TH INTERNATIONAL SYMPOSIUM ON ELECTRICAL APPARATUS AND TECHNOLOGIES (SIELA), 2018,
[6] Commercial hardware for artificial neural networks: A survey
Dias, FM
Antunes, A
Mota, AM
INTELLIGENT COMPONENTS AND INSTRUMENTS FOR CONTROL APPLICATIONS 2003, 2003, : 189 - 196
[7] ANALOG HARDWARE IMPLEMENTATIONS OF ARTIFICIAL NEURAL NETWORKS
Nedjah, Nadia
Da Silva, Rodrigo Martins
Mourelle, Luiza De Macedo
JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2011, 20 (03) : 349 - 373
[8] Artificial neural networks: a review of commercial hardware
Dias, FM
Antunes, A
Mota, AM
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2004, 17 (08) : 945 - 952
[9] Generating a large family of nonlinear activation functions (LFNAFs) in neural networks
Taheri, Morteza
Klidbary, Sajad Haghzad
JOURNAL OF SUPERCOMPUTING, 2025, 81 (05):
[10] Hardware implementation of radial-basis neural networks with Gaussian activation functions on FPGA
Shymkovych, Volodymyr
Telenyk, Sergii
Kravets, Petro
NEURAL COMPUTING & APPLICATIONS, 2021, 33 (15): : 9467 - 9479

← 1 2 3 4 5 →