SY Lin, JC Chiang - Microprocessors and Microsystems, 2023 - Elsevier
In the development of the neural network (NN), the activation function has become more and more important. The selection of the activation function indirectly affects the convergence …
Exponential functions are essential in many areas of science and engineering. Fast and efficient computing of such functions in multiple floating-point formats is a complex task for …
A Sehgal, AK Shukla, S Roy… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Spintronic devices have been considered a promising candidate for the hardware implementation of neural networks (NNs) due to their potential to address the contemporary …
H Geng, X Chen, N Zhao, Y Du… - IEEE Transactions on Very …, 2023 - ieeexplore.ieee.org
Piecewise polynomial approximation (PPA) on nonlinear functions plays an important role in high-precision computing. In this article, we proposed QPA, an integration of error-flattened …
C Ye, DS Jeong - IEEE Journal on Emerging and Selected …, 2023 - ieeexplore.ieee.org
Computing-in-memory (CIM) macros aiming at accelerating deep learning operations at low power need activation function (AF) units on the same die to reduce their host-dependency …
A Kumar, SS Sodhi - Journal of Intelligent & Fuzzy Systems, 2022 - content.iospress.com
We increase the power of the Artificial Neural Networks with the help of the Activation Function (AF). The tansig and logsig are widely used AF. But there is still requires some …
Oryctes rhinoceros poses a significant threat to coconut plants in several coconut-producing nations, including Rote Ndao District. Recognizing the distribution and severity of crop …
This dissertation presents symbolic loop compilation, the first full-fledged approach to symbolically map loop nests onto tightly coupled processor arrays (TCPAs), a class of loop …
Comparison of most used activation functions in deep neural networks and their circuit realizations in analog and digital neural Page 1 Comparison of most used activation …