Results 21 to 30 of about 10,487,885 (363)
Micromachines, 2021 Computing-In-Memory (CIM), based on non-von Neumann architecture, has lately received significant attention due to its lower overhead in delay and higher energy efficiency in convolutional and fully-connected neural network computing.
Siqiu Xu +5 more
doaj +1 more source
Problems Concerning Coefficients of Symmetric Starlike Functions Connected with the Sigmoid Function
Symmetry, 2023 In numerous geometric and physical applications of complex analysis, estimating the sharp bounds of coefficient-related problems of univalent functions is very important due to the fact that these coefficients describe the core inherent properties of ...
M. I. Faisal +4 more
semanticscholar +1 more source
BP Neural Network Fuse with Morphology Edge Detection Method
Journal of Harbin University of Science and Technology, 2021 In order to obtain better image edge information, an edge detection algorithm combining BP (Back Propagation) neural network and morphology is proposed.
YUE Xin-hua, DENG Cai-xia, ZHANG Zhao-ru
doaj +1 more source
IEEE Transactions on Computational Social Systems, 2023 This article proposes an agent-based policy simulation framework that can be applied to the cases satisfying: 1) the agents try to maximize some intertemporal preference and 2) the impacts of different factors on agents’ behavioral tendency are monotonic.
Songming Yu
semanticscholar +1 more source
Data‐driven performance metrics for neural network learning
International Journal of Adaptive Control and Signal Processing, EarlyView., 2023 Summary Effectiveness of data‐driven neural learning in terms of both local mimima trapping and convergence rate is addressed. Such issues are investigated in a case study involving the training of one‐hidden‐layer feedforward neural networks with the extended Kalman filter, which reduces the search for the optimal network parameters to a state ...
Angelo Alessandri +2 more
wiley +1 more source
Handling Vanishing Gradient Problem Using Artificial Derivative
IEEE Access, 2021 Sigmoid function and ReLU are commonly used activation functions in neural networks (NN). However, sigmoid function is vulnerable to the vanishing gradient problem, while ReLU has a special vanishing gradient problem that is called dying ReLU problem ...
Zheng Hu, Jiaojiao Zhang, Yun Ge
doaj +1 more source
Designing novel LDO voltage regulator implementation on FPGA using neural network [PDF]
Journal of Applied Research on Industrial Engineering, 2021 This paper describes a new technique for implementing an Artificial Neural Network (ANN) using Field Programmable Gate Array (FPGA). The goal is design the Low Drop Output (LDO) voltage-regulator circuit with the desired features depending on the ...
Mahdieh Jahangiri +2 more
doaj +1 more source
Robustness enhancement study of augmented positive identification controller by a sigmoid function
IAES International Journal of Artificial Intelligence (IJ-AI), 2023 The dissolved oxygen concentration in the wastewater treatment process (WWTP) must remain in a specific range while the factory operates. The augmented positive identification (PID) controller with a nonlinear element (sigmoid function) is proposed to ...
Abbas H. Issa +3 more
semanticscholar +1 more source
REAP-2: An interactive quantitative tool for robust and efficient dose-response curve estimation
Journal of Clinical and Translational Science, 2023 REAP-2 is an interactive dose-response curve estimation tool for Robust and Efficient Assessment of drug Potency. It provides user-friendly dose-response curve estimation for in vitro studies and conducts statistical testing for model comparisons with a ...
Xinying Fang +8 more
doaj +1 more source
Algorithms, 2023 Planning an achievable trajectory for a mobile robot usually consists of two steps: (i) finding a path in the form of a sequence of discrete waypoints and (ii) transforming this sequence into a continuous and smooth curve.
Svetlana A. Krasnova +3 more
doaj +1 more source