TY - JOUR
T1 - Novel Analog Implementation of a Hyperbolic Tangent Neuron in Artificial Neural Networks
AU - Shakiba, Fatemeh Mohammadi
AU - Zhou, Mengchu
N1 - Funding Information:
Manuscript received January 31, 2020; revised June 11, 2020 and September 3, 2020; accepted October 16, 2020. Date of publication November 4, 2020; date of current version July 19, 2021. This work was supported in part by the International S&T Cooperation Program of China under Grant 2013DFM10100. (Corresponding author: MengChu Zhou.) Fatemeh Mohammadi Shakiba is with the Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ 07102 USA (e-mail: Fm298@njit.edu).
Publisher Copyright:
© 1982-2012 IEEE.
PY - 2021/11
Y1 - 2021/11
N2 - Recently, enormous datasets have made power dissipation and area usage lie at the heart of designs for artificial neural networks (ANNs). Considering the significant role of activation functions in neurons and the growth of hardware-based neural networks like memristive neural networks, this work proposes a novel design for a hyperbolic tangent activation function (Tanh) to be used in memristive-based neuromorphic architectures. The purpose of implementing a CMOS-based design for Tanh is to decrease power dissipation and area usage. This design also increases the overall speed of computation in ANNs, while keeping the accuracy in an acceptable range. The proposed design is one of the first analog designs for the hyperbolic tangent and its performance is analyzed by using two well-known datsets, including the Modified National Institute of Standards and Technology (MNIST) and Fashion-MNIST. The direct implementation of the proposed design for Tanh is proposed and investigated via software and hardware modeling.
AB - Recently, enormous datasets have made power dissipation and area usage lie at the heart of designs for artificial neural networks (ANNs). Considering the significant role of activation functions in neurons and the growth of hardware-based neural networks like memristive neural networks, this work proposes a novel design for a hyperbolic tangent activation function (Tanh) to be used in memristive-based neuromorphic architectures. The purpose of implementing a CMOS-based design for Tanh is to decrease power dissipation and area usage. This design also increases the overall speed of computation in ANNs, while keeping the accuracy in an acceptable range. The proposed design is one of the first analog designs for the hyperbolic tangent and its performance is analyzed by using two well-known datsets, including the Modified National Institute of Standards and Technology (MNIST) and Fashion-MNIST. The direct implementation of the proposed design for Tanh is proposed and investigated via software and hardware modeling.
KW - Artificial neural network (ANN)
KW - activation function
KW - hardware implementation
KW - hyperbolic tangent
KW - machine learning
KW - memristive neural network (MNN)
KW - neuromorphic architecture
UR - http://www.scopus.com/inward/record.url?scp=85096824253&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096824253&partnerID=8YFLogxK
U2 - 10.1109/TIE.2020.3034856
DO - 10.1109/TIE.2020.3034856
M3 - Article
AN - SCOPUS:85096824253
SN - 0278-0046
VL - 68
SP - 10856
EP - 10867
JO - IEEE Transactions on Industrial Electronics
JF - IEEE Transactions on Industrial Electronics
IS - 11
M1 - 9248592
ER -