Results 131 to 140 of about 22,674 (253)

Non-Iterative Phase-Only Hologram Generation via Stochastic Gradient Descent Optimization

Photonics
In this work, we explored, for the first time, to the best of our knowledge, the potential of stochastic gradient descent (SGD) to optimize random phase functions for application in non-iterative phase-only hologram generation.
Alejandro Velez-Zea, John Fredy Barrera-Ramírez   +1 more
doaj   +1 more source

The inverse variance-flatness relation in stochastic gradient descent is critical for finding flat minima. [PDF]

Proc Natl Acad Sci U S A, 2021
Feng Y, Tu Y.
europepmc   +1 more source

Dual Stochastic Natural Gradient Descent

CoRR, 2020
[EN] Although theoretically appealing, Stochastic Natural Gradient Descent (SNGD) is computationally expensive, it has been shown to be highly sensitive to the learning rate, and it is not guaranteed to be convergent. Convergent Stochastic Natural Gradient Descent (CSNGD) aims at solving the last two problems.
Sánchez-López, Borja, Cerquides, Jesús   +1 more
openaire   +2 more sources

Advances and Perspectives in Graphene‐Based Quantum Dots Enabled Neuromorphic Devices

Advanced Science, EarlyView.
Graphene‐based QDs are zero‐dimensional carbon nanomaterials with pronounced quantum confinement and tunable electronic structures. Herein, we summarize their synthesis strategies and functionalization methods, and highlight their functional roles and operating mechanisms in devices, as well as recent advances in neuromorphic electronics. We anticipate
Yulin Zhen, Wei Zeng, Zherui Zhao, JiYu Zhao, Ziyan Huang, Zhuo Chen, Kui Zhou, Guanglong Ding, Su‐Ting Han, Ye Zhou   +9 more
wiley   +1 more source

Sentiment classification for employees reviews using regression vector- stochastic gradient descent classifier (RV-SGDC). [PDF]

PeerJ Comput Sci, 2021
Gaye B, Zhang D, Wulamu A.
europepmc   +1 more source

A Crack‐Based One‐Dimensional Microspheres Array Enables Thermal–Mechanical Decoupled Dual‐Functional Sensing

Advanced Science, EarlyView.
Inspired by Nostoc, a crack‐based one‐dimensional microspheres array (COMA) sensor is developed, which stabilizes crack geometry under isotropic expansion, enabling a predictable, monotonic thermal response from which true strain can be accurately extracted. The COMA sensor exhibits high sensitivity at ultralow deformation (gauge factor up to 89) and a
Wanqing Xu, Hongyi Tu, Zehao Wang, Tianyu Zhu, Chao Wang, Min Chen, Lan Shi, Limin Wu   +7 more
wiley   +1 more source

An Improved Reacceleration Optimization Algorithm Based on the Momentum Method for Image Recognition

Mathematics
The optimization algorithm plays a crucial role in image recognition by neural networks. However, it is challenging to accelerate the model’s convergence and maintain high precision.
Haijing Sun, Ying Cai, Ran Tao, Yichuan Shao, Lei Xing, Can Zhang, Qian Zhao   +6 more
doaj   +1 more source

Triple‐Mode Ferroelectric Thin‐Film Transistor for Hybrid Electrical–Optical Reservoir Computing

Advanced Science, EarlyView.
A triple‐mode ferroelectric thin‐film transistor is developed by integrating Si3N4/HZO/IGZO layers to realize three independent memory modes: electric long‐term, electric short‐term, and optical short‐term. This single‐device architecture functions as both a reservoir and readout layer, achieving 92.43% MNIST accuracy. It offers a fully hardware‐based,
Hyeonho Lee, Seungjun Lee, Tae‐Hyeon Kim, Yonghee Jeong, Gwangmin An, Minsu Ko, Junsu Yu, Heung Soo Kim, Yang Chai, Sungjun Kim   +9 more
wiley   +1 more source

Shear‐Induced Emergence of Aromatic Superlow‐Friction Interfaces in Amorphous Carbon: Triggering Chemical Impurities and Atomic‐Scale Mechanisms

Advanced Science, EarlyView.
High‐throughput quantum‐mechanical simulations reveal that amorphous carbon undergoes shear‐driven structural transformation into aromatic, graphene‐like interfaces. This mechanochemical process is governed by dopant chemistry: dopants with valency less than four promote the emergence of superlow‐friction amorphous graphene, whereas tetra‐valent ...
Takuya Kuwahara, Koki Horiguchi, Leonhard Mayrhofer, Gianpietro Moras, Michael Moseler   +4 more
wiley   +1 more source

Tunable Dynamics via Dual‐Ion Modulation for Event‐based Data Processing Using a Highly Uniform and Self‐Rectifying Memristor Array

Advanced Science, EarlyView.
Tunable dynamics of an interface‐type memristor array enabled by dual‐ion modulation through Ag nanoclusters are demonstrated. A 32 × 32 one‐resistor (1R) array exhibits 100% yield with high temporal/spatial uniformity (<3%) and a rectification ratio of 105.
Yoonho Cho, Dawon Kim, Jeonghong Lee, Dae‐won Kim, See‐On Park, Jongmin Bae, Taehwan Jang, Shinhyun Choi   +7 more
wiley   +1 more source