Results 71 to 80 of about 28,952 (292)

Text Sentiment Analysis Based on Hybrid Chi-square Statistic and Logistic Regression [PDF]

Jisuanji gongcheng, 2017
In text sentiment analysis,feature extraction method based on Chi-square statistic (CHI) is easy to ignore single text word frequency which leads to text feature accuary is low,a feature extraction method based on hybrid chi-square statistics is proposed.
LI Ping,DAI Yueming,WANG Yan
doaj   +1 more source

Fractional Stochastic Search Algorithms: Modelling Complex Systems via AI

Mathematics, 2023
The aim of this article is to establish a stochastic search algorithm for neural networks based on the fractional stochastic processes {BtH,t≥0} with the Hurst parameter H∈(0,1).
Bodo Herzog
doaj   +1 more source

All‐in‐One Analog AI Hardware: On‐Chip Training and Inference with Conductive‐Metal‐Oxide/HfOx ReRAM Devices

Advanced Functional Materials, EarlyView.
An all‐in‐one analog AI accelerator is presented, enabling on‐chip training, weight retention, and long‐term inference acceleration. It leverages a BEOL‐integrated CMO/HfOx ReRAM array with low‐voltage operation (<1.5 V), multi‐bit capability over 32 states, low programming noise (10 nS), and near‐ideal weight transfer.
Donato Francesco Falcone, Victoria Clerico, Wooseok Choi, Tommaso Stecconi, Folkert Horst, Laura Bégon‐Lours, Matteo Galetta, Antonio La Porta, Nikhil Garg, Fabien Alibart, Bert Jan Offrein, Valeria Bragaglia   +11 more
wiley   +1 more source

Intermediate Resistive State in Wafer‐Scale Vertical MoS2 Memristors Through Lateral Silver Filament Growth for Artificial Synapse Applications

Advanced Functional Materials, EarlyView.
In MOCVD MoS2 memristors, a current compliance‐regulated Ag filament mechanism is revealed. The filament ruptures spontaneously during volatile switching, while subsequent growth proceeds vertically through the MoS2 layers and then laterally along the van der Waals gaps during nonvolatile switching.
Yuan Fa, Milan Buttberg, Ke Ran, Rana Walied Ahmad, Dennis Braun, Lukas Völkel, Jimin Lee, Sofía Cruces, Bart Macco, Bárbara Canto, Holger Lerch, Thorsten Wahlbrink, Holger Kalisch, Michael Heuken, Andrei Vescan, Joachim Mayer, Zhenxing Wang, Ilia Valov, Stephan Menzel, Max C. Lemme   +19 more
wiley   +1 more source

Stochastic gradient descent with finite samples sizes

, 2016
The minimization of empirical risks over finite sample sizes is an important problem in large-scale machine learning. A variety of algorithms has been proposed in the literature to alleviate the computational burden per iteration at the expense of ...
Ali H. Sayed, Bicheng Ying, Ying, Bicheng, Kun Yuan, Yuan, Kun, Sayed, Ali H, Stefan Vlaski, Vlaski, Stefan   +7 more
core   +2 more sources

Integration of Low‐Voltage Nanoscale MoS2 Memristors on CMOS Microchips

Advanced Functional Materials, EarlyView.
This article presents the first monolithic integration of nanoscale MoS2‐based memristors into the back‐end‐of‐line of foundry‐fabricated CMOS microchips in a one‐transistor‐one‐resistor (1T1R) architecture. The MoS2‐based 1T1R cells exhibit forming‐free, nonvolatile resistive switching with ultra‐low operating voltages, low cycle‐to‐cycle variability ...
Jimin Lee, Sofía Cruces, Xiaohua Liu, Yang Chen, Vasilis A. Maroufidis, Janghyun Jo, Lukas Völkel, Dennis Braun, Michael Möller, Leon Brackmann, Holger Kalisch, Michael Heuken, Andrei Vescan, Rafal E. Dunin‐Borkowski, Joachim Mayer, Stefan Wiefels, Max C. Lemme   +16 more
wiley   +1 more source

On the Generalization of Stochastic Gradient Descent with Momentum

J. Mach. Learn. Res., 2018
While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that there exists a convex loss function for which the stability gap for multiple epochs of SGD with ...
Ali Ramezani-Kebrya, Kimon Antonakopoulos, Volkan Cevher, Ashish Khisti, Ben Liang 0001   +4 more
openaire   +3 more sources

Attentional-Biased Stochastic Gradient Descent

Trans. Mach. Learn. Res., 2020
In this paper, we present a simple yet effective provable method (named ABSGD) for addressing the data imbalance or label noise problem in deep learning. Our method is a simple modification to momentum SGD where we assign an individual importance weight to each sample in the mini-batch.
Qi Qi 0006, Yi Xu 0008, Wotao Yin, Rong Jin 0001, Tianbao Yang   +4 more
openaire   +3 more sources

Integrated Field‐Free SOT Domain‐Wall Synapses and MTJ Stochastic Neurons for Hardware Boltzmann Machines

Advanced Functional Materials, EarlyView.
Field‐free spin‐orbit torque domain‐wall synapses integrated with stochastic MTJ neurons enable compact hardware Boltzmann machines. Leveraging intrinsic stochasticity and multi‐level conductance, the system achieves efficient probabilistic learning with high accuracy, demonstrating a scalable spintronic platform for energy‐efficient edge AI.
Aijaz H. Lone, Meng Tang, Camelia Florica, Bin He, Jingkai Xu, Selma Amara, Georgian Melinte, Xixiang Zhang, Gianluca Setti   +8 more
wiley   +1 more source

Accelerating Asynchronous Stochastic Gradient Descent for Neural Machine Translation [PDF]

, 2018
In order to extract the best possible performance from asynchronous stochastic gradient descent one must increase the mini-batch size and scale the learning rate accordingly.
Junczys-Dowmunt, Marcin, Nikolay Bogoychev, Alham Fikri Aji, Kenneth Heafield, Bogoychev, Nikolay, Heafield, Kenneth, Aji, Alham, Marcin Junczys-Dowmunt   +7 more
core   +1 more source