Results 1 to 10 of about 10,610,136 (340)

Gaussian‐Sigmoid Reinforcement Transistors: Resolving Exploration‐Exploitation Trade‐Off Through Gate Voltage‐Controlled Activation Functions

Advanced Functional Materials, EarlyView.
The characteristics of a vertical n–p–i–p heterostructure transistor device, which exhibits a voltage‐tunable transition between Gaussian and sigmoid functions, are investigated. The mixed state of the transfer curve enables the utilization of both exploitation and exploration, improving computational performance in reinforcement learning tasks ...
Jisoo Park, Juhyung Seo, Ryun‐Han Koo, Dinithi Jayasuriya, Nethmi Jayasinghe, Wonjun Shin, Amit Ranjan Trivedi, Hocheon Yoo   +7 more
openalex   +2 more sources

Evaluation of Major Soil Nutrients After Application of Microbial-Inoculated Acidified Biochar Pellets Using a Sigmoid Function

JooHee Nam, JoungDu Shin, Jae‐Young Choi, Sang‐Won Park, Jae Wook Chung, Changyoon Jeong   +5 more
openalex   +1 more source

Machine learning-based prediction of compressive energy absorption in shoe soles with different features. [PDF]

Sci Rep
Mohammadi MM, Nourani A.
europepmc   +1 more source

Clock Glitch Fault Attacks on Deep Neural Networks and Their Countermeasures. [PDF]

Sensors (Basel)
Lee S, Kim S, Hong S, Ha J.
europepmc   +1 more source

Laparoscopic primary suture repair of sigmoid perforation due to a chicken bone: a case report. [PDF]

J Surg Case Rep
Borgas P, Bath MF, Jama I, Theodoropoulos C, Guru Naidu S.   +4 more
europepmc   +1 more source

Thermodynamic analysis and intelligent modeling of statin drugs solubility in supercritical carbon dioxide. [PDF]

Sci Rep
Amani M, Shahrabadi A, Ardestani NS.
europepmc   +1 more source

Analyzing industrial robot selection based on a fuzzy neural network under triangular fuzzy numbers. [PDF]

Sci Rep
Ullah I, Abdullah S, Rahimzai AA, Nawaz M, Khan S.   +4 more
europepmc   +1 more source

Sigmoid Function Model for a PWM DC–DC Converter

IEEE transactions on power electronics, 2023
Considering the presence of switching devices, a pulse-width modulation (PWM) dc–dc converter is a piecewise smooth switching system that causes difficulties in stability analysis and controller design. Hence, a new modeling method that employs a sigmoid
Yimin Lu, Shiwu Zhong
semanticscholar   +1 more source

A Modular Approximation Methodology for Efficient Fixed-Point Hardware Implementation of the Sigmoid Function

IEEE transactions on industrial electronics (1982. Print), 2022
The sigmoid function is a widely used nonlinear activation function in neural networks. In this article, we present a modular approximation methodology for efficient fixed-point hardware implementation of the sigmoid function.
Zhe Pan, Zonghua Gu, Xiaohong Jiang, Guoquan Zhu, De Ma   +4 more
semanticscholar   +1 more source

Design and FPGA Implementation of the LUT based Sigmoid Function for DNN Applications

International Symposium on Smart Electronic Systems, 2022
Nowadays deep learning algorithms are became popular in the field of biomedical applications for automatic classification and detection problems. There are multiple issues in implementing these algorithms on digital platform.
Revathi Pogiri, S. Ari, K. Mahapatra
semanticscholar   +1 more source