Results 101 to 110 of about 7,740,063 (200)
SensorsThis paper investigates the application of ensemble learning techniques, specifically meta-learning, in intrusion detection systems (IDS) for the Internet of Medical Things (IoMT).
Mousa Alalhareth, Sung-Chul Hong
doaj +1 more source
A learning theory of meta learning
National Science ReviewThis paper gives a brief introduction to recent theoretical advance of meta learning.
openaire +2 more sources
Informe de práctica empresarial, Comisaría de Familia de Guamal
, 2023 Las Comisarías de Familia son la puerta de entrada para el acceso a la justicia que tienen las víctimas de violencia intrafamiliar, la cual conlleva de manera implícita la violación de los derechos humanos, repercute en el ámbito de la integridad física ...
Cárdenas Chaparro, Ingrid Julieth
core
Reliability estimation in regression supported with meta-learning and principal component analysis [PDF]
, 2010 Reliability estimation in regression supported with meta-learning and principal component analysis Reliability estimates for individual predictions can provide important risk-sensitive information.
Radović, Marija
core +1 more source
IEEE Open Journal of the Communications SocietyPedestrian re-identification (Re-ID) leverages cross-camera data acquired by the Internet of Things (IoT) devices and sensors to identify, monitor, and analyze pedestrians, allowing IoT applications to provide more intelligent, secure, and tailored ...
Xiting Peng +4 more
doaj +1 more source
Privacy Challenges in Meta-Learning: An Investigation on Model-Agnostic Meta-Learning
CoRRMeta-learning involves multiple learners, each dedicated to specific tasks, collaborating in a data-constrained setting. In current meta-learning methods, task learners locally learn models from sensitive data, termed support sets. These task learners subsequently share model-related information, such as gradients or loss values, which is computed ...
Mina Rafiei +2 more
openaire +2 more sources
On the ERM Principle in Meta-Learning
CoRRClassic supervised learning involves algorithms trained on $n$ labeled examples to produce a hypothesis $h \in \mathcal{H}$ aimed at performing well on unseen examples. Meta-learning extends this by training across $n$ tasks, with $m$ examples per task, producing a hypothesis class $\mathcal{H}$ within some meta-class $\mathbb{H}$. This setting applies
Yannay Alon +3 more
openaire +2 more sources
Meta-learning with stochastic linear bandits
, 2020 We investigate meta-learning procedures in the setting of stochastic linear bandits tasks. The goal is to select a learning algorithm which works well on average over a class of bandits tasks, that are sampled from a task-distribution. Inspired by recent
Pontil M., Lazaric A., Cella L.
core +1 more source
Meta-learning of instance selection for data summarization
, 2011 Meta-learning of instance selection for data ...
K Smith-Miles (9863015) +1 more
core
Linking meta-learning to meta-structure
Schilling M, Ritter H, Ohl FW. Linking meta-learning to meta-structure. Behavioral and Brain Sciences . 2024;47: e164.We propose that a principled understanding of meta-learning, as aimed for by the authors, benefits from linking the focus on learning ...
Schilling, Malte +2 more
core +1 more source