Results 81 to 90 of about 1,295,192 (344)

The Marginal Value of Adaptive Gradient Methods in Machine Learning

, 2017
Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural networks. Examples include AdaGrad, RMSProp, and Adam. We show that for simple overparameterized problems, adaptive methods often find drastically different solutions than ...
Wilson, Ashia C., Roelofs, Rebecca, Stern, Mitchell, Srebro, Nathan, Recht, Benjamin   +4 more
openaire   +2 more sources

Patterning the Void: Combining L‐Systems with Archimedean Tessellations as a Perspective for Tissue Engineering Scaffolds

Advanced Functional Materials, EarlyView.
This study introduces a novel multi‐scale scaffold design using L‐fractals arranged in Archimedean tessellations for tissue regeneration. Despite similar porosity, tiles display vastly different tensile responses (1–100 MPa) and deformation modes. In vitro experiments with hMSCs show geometry‐dependent growth and activity. Over 55 000 tile combinations
Maria Kalogeropoulou, Kenny A. van Kampen, Pierpaolo Fucile, Carlos Mota, Lorenzo Moroni   +4 more
wiley   +1 more source

Minimum Density Hyperplanes [PDF]

, 2016
Associating distinct groups of objects (clusters) with contiguous regions of high probability density (high-density clusters), is central to many statistical and machine learning approaches to the classification of unlabelled data.
Hofmeyr, David P., Pavlidis, Nicos G., Tasoulis, Sotiris K.   +2 more
core   +2 more sources

Spectrally Tunable 2D Material‐Based Infrared Photodetectors for Intelligent Optoelectronics

Advanced Functional Materials, EarlyView.
Intelligent optoelectronics through spectral engineering of 2D material‐based infrared photodetectors. Abstract The evolution of intelligent optoelectronic systems is driven by artificial intelligence (AI). However, their practical realization hinges on the ability to dynamically capture and process optical signals across a broad infrared (IR) spectrum.
Junheon Ha, Yingshan Ma, Yong Nam An, Sung‐Un An, Hyeon Hak Jung, Suvi‐Tuuli Varjamo, Jiwon Yoo, Junho Min, Hanvit Kim, Faisal Ahmed, Sang Hoon Chae, Young Min Song, Weiwei Cai, Tawfique Hasan, Zhipei Sun, Dong‐Ho Kang, Hyeon‐Jin Shin, Yunyun Dai, Hoon Hahn Yoon   +18 more
wiley   +1 more source

Optimization of Short-Term Relaxation Effect by Dual Error Margin Scheme for Resistive Random-Access Memory-Based Next Generation Reservoir Computing

IEEE Journal of the Electron Devices Society
Next Generation Reservoir Computing (NGRC) has demonstrated strong potential in hardware-based machine learning applications, leveraging RRAM for efficient feature vector generation.
Qingyun Zuo, Danian Dong, Xiaoxin Xu, Woyu Zhang, Dashan Shang, Xu Zheng, Wenxuan Sun, Hao Min   +7 more
doaj   +1 more source

Zoomed Response Surface Method for Automatic Design in Parameters Optimization of Low-Voltage Power MOSFET

IEEE Journal of the Electron Devices Society, 2022
A new parameter optimization method using zoomed response surface (RS) is proposed for automatic design of low-voltage power MOSFET. Low-voltage MOSFET characteristics have been improved continuously considering with not only low power loss but also low ...
Wataru Saito, Shin-Ichi Nishizawa
doaj   +1 more source

Protection against failure of machine-learning-based QoT prediction

Journal of Optical Communications and Networking, 2021
Machine learning (ML)-based methods are being widely explored to predict the quality of transmission (QoT) of a lightpath. They are expected to reduce the signal-to-noise ratio margin reserved for the lightpath, thus improving the spectrum efficiency of ...
Ningning Guo, Longfei Li, B. Mukherjee, G. Shen   +3 more
semanticscholar   +1 more source

Digital Discovery of Synthesizable Metal−Organic Frameworks via Molecular Dynamics‑Informed, High‑Fidelity Deep Learning

Advanced Functional Materials, EarlyView.
Tabular foundation model interrogates the synthetic likelihood of metal−organic frameworks. Abstract Metal–organic frameworks (MOFs) are celebrated for their chemical and structural versatility, and in‑silico screening has significantly accelerated their discovery; yet most hypothetical MOFs (hMOFs) never reach the bench because their synthetic ...
Xiaoyu Wu, Rui Zheng, Quan Liu, Jianwen Jiang   +3 more
wiley   +1 more source

From In‐Silico Optimized Microfabrication to Experimental Validation: Engineering a Tridimensional Epi‐Intraneural Interface

Advanced Functional Materials, EarlyView.
An epi‐intraneural interface is developed through in silico optimization and a novel tridimensional microfabrication pipeline. The device integrates penetrating and epineural contacts on a flexible substrate. Mechanical, electrochemical, and in vivo testing in rat and pig reveal robust implantation, low‐threshold activation, and site‐dependent ...
Federico Ciotti, Andrea Cimolato, Noemi Gozzi, Pietro Palopoli, Luca Brugnoli, Natalija Katic Secerovic, Rebecca Gallivan, Alexander Shokurov, Carlo Menon, Johannes Weichart, Ignacio Delgado‐Martinez, Weiguo Song, Stavros Zanos, Xavier Navarro, Stanisa Raspopovic   +14 more
wiley   +1 more source

Study Comparison Deep Learning and Support Vector Machine for Face Mask Detection

Aceh International Journal of Science and Technology
Deep Learning (DL) and Support Vector Machine (SVM) was used for a plethora number of researches lately. Deep Learning works by representing data in layers of learning layers so that the representation becomes more meaningful, and Support Vector Machine ...
Rani Kurnia Putri, Muhammad Athoillah*
doaj   +1 more source