Maml - Open Access .click

Communications in Computer and Information Science, 2023
In this study, we propose a TripletMAML algorithm as an extension to Model-Agnostic Meta-Learning (MAML) which is the most widely-used optimization-based meta-learning algorithm. We approach MAML from a metric-learning perspective and train it using meta-learning tasks composed of triplets of images.
Ayla Gülcü, İsmail Taha Samed Özkan, Zeki Kuş +2 more
exaly +3 more sources

MAML-SAMIoT: A cloud-fog computing and MAML-based few-shot IoT intrusion detection model

Computer Networks
刘振鹏刘
exaly +2 more sources

Investigating Parallelization of MAML

2020
We propose a meta-learning framework to distribute Model-Agnostic Meta-Learning (DMAML), a widely used meta-learning algorithm, over multiple workers running in parallel. DMAML enables us to use multiple servers for learning and might be crucial if we want to tackle more challenging problems that often require more CPU time for simulation. In this work,
Jan Bollenbacher +3 more
openaire +1 more source

Business apps with MAML

Proceedings of the Symposium on Applied Computing, 2017
Business apps support the digitalization of business operations by utilizing the potential of ubiquitous mobile devices. Whereas many frameworks for programming cross-platform apps exist, few modeling approaches focus on platform-agnostic representations of mobile apps.
openaire +1 more source

fos: computer and information sciences
computer science - machine learning
machine learning cs.lg

meta-learning
statistics - machine learning
machine learning stat.ml

few-shot learning
artificial intelligence cs.ai
computer science - artificial intelligence