Results 101 to 110 of about 7,049,980 (289)

Pretraining Client Selection Algorithm Based on a Data Distribution Evaluation Model in Federated Learning

IEEE Access
Federated Learning (FL) allows task initiators (servers) to utilize data from task participants (clients) to train machine learning models while protecting data privacy.
Chang Xu, Hong Liu, Kexin Li, Wanglei Feng, Wei Qi   +4 more
doaj   +1 more source

Homologous membrane wrapped ZIF‐8 nanoparticles accelerate differentiation of neural stem cell for spinal cord injury therapy

BMEMat, EarlyView.
Homologous membrane wrapped ZIF‐8 nanoparticles were proposed to improve biocompatibility and targeting ability to neural stem cells (NSCs). ZIF‐8‐SCM NPs exhibit pH responsiveness, thereby generating an intracellular Zn2+ storm to accelerate neural differentiation through calcium and MAPK signaling pathways. Moreover, they promote function recovery in
Jie Wang, Lusen Shi, Xinhui Liu, Zhong Zhuang, Zhichao Feng, Chunhui Sun, Jingang Wang, Nik Ahmad Nizam Nik Malek, Wan Hairul Anuar Kamaruddin, Shuping Wang, Hengxing Zhou, Na Ren   +11 more
wiley   +1 more source

Weighting non-IID batches for out-of-distribution detection

Machine Learning
AbstractA standard network pretrained on in-distribution (ID) samples could make high-confidence predictions on out-of-distribution (OOD) samples, leaving the possibility of failing to distinguish ID and OOD samples in the test phase. To address this over-confidence issue, the existing methods improve the OOD sensitivity from modeling perspectives, i.e.
Zhi-Lin Zhao 0001, Longbing Cao
openaire   +1 more source

What Constitutes an Attractive Product‐as‐a‐Service Offer? Examining Consumer Preferences for (Circular) Business Patterns

Business Strategy and the Environment, EarlyView.
ABSTRACT Little is known about consumer preferences for combinations of circular business model patterns, despite their potential to benefit the design of product services. This study examines consumer preferences for product‐as‐a‐service offers, combined with circular product attributes, across Sweden and the Netherlands.
Steven Sarasini, Aemiro Melkamu Daniel, Katherine Whalen, Nancy Bocken, Agnieszka Hunka, Tarlan Ahmadov   +5 more
wiley   +1 more source

Overcoming Forgetting in Federated Learning on Non-IID Data

CoRR, 2019
We tackle the problem of Federated Learning in the non i.i.d. case, in which local models drift apart, inhibiting learning. Building on an analogy with Lifelong Learning, we adapt a solution for catastrophic forgetting to Federated Learning. We add a penalty term to the loss function, compelling all local models to converge to a shared optimum. We show
Neta Shoham, Tomer Avidor, Aviv Keren, Nadav Israel, Daniel Benditkis, Liron Mor-Yosef, Itai Zeitak   +6 more
openaire   +2 more sources

Non-IID recommender systems : a machine learning approach [PDF]

, 2018
University of Technology Sydney. Faculty of Engineering and Information Technology.A recommender system (RS) comprises the core software, tools, and techniques that effectively and efficiently cope with information overload as well as locate information ...
Hu, Liang
core  

Multivariate phase‐dependent optimization of bioprocesses boosts performance and quality—Why timing (of exposure) matters

Biotechnology Progress, EarlyView.
Abstract Applying a single parameter set to describe complex mammalian kinetics often is too simplistic, as it fails to capture sensitive cell‐to‐environment interactions that may be exploited to optimize production performance. To resolve this time dependency, intra‐experimental parameter shifts as part of design of dynamic experiments (DoDE) can be ...
Samuel Kienzle, Lisa Junghans, Anja Wittmann, Stefan Wieschalka, Ralf Takors, Nicole Erika Radde, Beate Presser, Verena Nold   +7 more
wiley   +1 more source

CHPFL: Clustered adaptive hierarchical federated learning for edge-level personalization

High-Confidence Computing
Federated learning faces challenges with non-IID data distributions, often resulting in suboptimal performance for individual clients with the global model. To address this issue, we propose a clustered hierarchical personalized federated learning (CHPFL)
Lihua Song, Jing Li, Honglu Jiang, Shuhua Wei, Yufei Guo   +4 more
doaj   +1 more source

Jackknife bias‐corrected variance estimation for the generalized regression estimator

Canadian Journal of Statistics, EarlyView.
Abstract Commonly used variance estimators for the generalized regression estimator (GREG) are based on Taylor linearization and jackknife. Traditionally, a jackknife GREG variance estimator is obtained by jackknifing GREG, which consists of computing GREG from each of several subsamples of the parent sample, and estimating the variance of the parent ...
Marius Stefan, J.N.K Rao
wiley   +1 more source

Edge-Federated Learning-Based Intelligent Intrusion Detection System for Heterogeneous Internet of Things

IEEE Access
Distributed denial of service (DDoS) is an awful cyber threat, becoming more prevalent with mature heterogeneous IoT (HetIoT) applications like intelligent agriculture, wearables, and self-driving cars. Developing intelligent intrusion detection systems (
Shalaka S. Mahadik, Pranav M. Pawar, Raja Muthalagu   +2 more
doaj   +1 more source