Results 81 to 90 of about 54,299 (266)

Convexified Convolutional Neural Networks

CoRR, 2016
We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing the nonlinear convolutional filters as vectors in a reproducing kernel Hilbert space, the CNN parameters can be represented as a low-rank matrix, which can be relaxed to ...
Yuchen Zhang 0002, Percy Liang, Martin J. Wainwright   +2 more
openaire   +3 more sources

A Practical Noise2Noise Denoising Pipeline for High‐Throughput Raman Spectroscopy

Advanced Engineering Materials, EarlyView.
A lightweight and reproducible denoising pipeline for high‐throughput Raman spectroscopy is introduced, based on a 1D convolutional autoencoder trained with a Noise2Noise strategy. Using only repeated short‐exposure acquisitions, the method suppresses stochastic noise without reference spectra, enabling reliable spectral reconstruction while preserving
David Martin‐Calle, Cesar Alvarez‐Llamas, Vincent Motto‐Ros, Christophe Dujardin, Jérémie Margueritat, David Rodney   +5 more
wiley   +1 more source

HexagDLy—Processing hexagonally sampled data with CNNs in PyTorch

SoftwareX, 2019
HexagDLy is a Python-library extending the PyTorch deep learning framework with convolution and pooling operations on hexagonal grids. It aims to ease the access to convolutional neural networks for applications that rely on hexagonally sampled data as ...
Constantin Steppa, Tim L. Holch
doaj   +1 more source

Quantifying Subsurface Weak in‐Plane Magnetization of Mixed Phase BiFeO3 by Scanning Nitrogen Vacancy Magnetometry

Advanced Functional Materials, EarlyView.
We use scanning nitrogen vacancy magnetometry to directly image the weak in‐plane magnetic moments in mixed phase BiFeO3 at the nanoscale and quantify the local magnetic moments to be 18.8±2.0 μB/nm2 in the rhombohedral‐like phase and 1.5±0.6 μB/nm2 in the well‐known non‐magnetic tetragonal‐like phase.
Lei Wang, Zhewen Xu, Yuwen Xu, Björn Josteinsson, Simon Josephy, Dawei Zhang, Yunlong Sun, Heung‐Sik Park, Jihun Kim, Kanghyun Chu, Kyung Song, Danyang Wang, Chan‐Ho Yang, Andrea Morales, Jan Seidel   +14 more
wiley   +1 more source

Performance Enhancement of Tin Chloride‐Incorporated Ferroelectric Polymer‐Based Artificial Synapse for Hardware Neural Networks

Advanced Functional Materials, EarlyView.
This paper proposes a highly efficient ferroelectric artificial synapse device based on an oxide semiconductor and SnCl2‐inserted P(VDF‐TrFE) gate dielectric layer. This FeFET significantly improved the synaptic performance due to the ion‐dipole interaction.
Hyun‐Soo Kim, Hyunkyu Lee, Yeonho Choi, Won Young Jang, Hyungmin Kim, Krishna Moorthy Ponnusamy, Hongseung Lee, Jaewook Yoo, Ji Ye Lee, S. Chandramohan, Seongin Hong, Hagyoul Bae, Hyeon‐Sik Jang, Sang Yeol Lee, Keun Heo   +14 more
wiley   +1 more source

Noise‐Limited Bit Precision in Ferroelectric Synaptic Transistors for High‐Resolution Neuromorphic Computing

Advanced Functional Materials, EarlyView.
Low‐frequency noise spectroscopy defines the resolvable conductance states of synaptic FeFETs by coupling read‐current fluctuation with usable dynamic range. The resulting noise‐limited bit precision establishes a universal, device‐agnostic reliability metric beyond the memory window, enabling quantitative benchmarking and rational design of high ...
Jaehong Park, Yeonseop Shin, Changhyeon Han, Sangwoo Kim, Eunchan Park, Youngchan Cho, Jaehong Min, Hyunjun Ahn, Jaekyoung Park, Cheol‐Woong Yang, Jangsaeng Kim, Daewoong Kwon, Wonjun Shin   +12 more
wiley   +1 more source

On-chip photoelectric hybrid convolutional accelerator based on Bragg grating array

Results in Physics
We propose an on-chip photoelectric hybrid convolution accelerator based on Bragg grating array. The weight of the convolution kernel can be adjusted by controlling the central wavelengths of the Bragg grating array.
Kaiteng Cai, Liqi Chen, Yunming Zhang, Juncheng Wang, Wei Lin, Shaoxiang Duan, Bo Liu   +6 more
doaj   +1 more source

Reconfigurable Au Nanoparticle Monolayers on Regenerated Cellulose Hydrogels: Highly Sensitive SERS Detection of Polystyrene Micro/Nanoplastics With Interpretable Deep Learning

Advanced Functional Materials, EarlyView.
A regenerated cellulose (RC) hydrogel‐based SERS substrate integrating a Marangoni‐transferred gold nanoparticle self‐assembled monolayer (Au‐SAM) is fabricated. Reswelling‐induced hotspot formation enhances polystyrene micro/nanoplastics (PS MNPs) detection in complex matrices, providing reproducible, high‐throughput SERS signals across diverse ...
Youngho Jeon, Yu‐Jin Jeon, Suji Lee, Jeseong Kim, Dae‐Hyun Jung, Jungmok You   +5 more
wiley   +1 more source

Wearable Kirigami‐Apertured Capacitive Sensors for Continuous Cardiac Volumetric Monitoring

Advanced Functional Materials, EarlyView.
A wearable kirigami‐apertured carbon nanotube‐paper composite (K‐CPC) capacitive sensor enables cardiac volumetric monitoring. The kirigami process creates a central aperture with cantilevered fibers that confine the electric field, enhancing both sensitivity and lateral resolution.
Yu‐Jen Cheng, Shawn Kim, Jonathan Avery, Younghoon Kwon, Jae‐Hyun Chung   +4 more
wiley   +1 more source

Understanding Convolutional Neural Networks

CoRR, 2016
Statistical Machine Learning Course Project at Carnegie Mellon ...
openaire   +2 more sources