Results 21 to 30 of about 187,533 (264)
Metrics and Continuity in Reinforcement Learning
Proceedings of the AAAI Conference on Artificial Intelligence, 2021 In most practical applications of reinforcement learning, it is untenable to maintain direct estimates for individual states; in continuous-state systems, it is impossible. Instead, researchers often leverage {\em state similarity} (whether explicitly or implicitly) to build models that can generalize well from a limited set of samples.
Charline Le Lan +2 more
openaire +2 more sources
Pacing Electrocardiogram Detection With Memory-Based Autoencoder and Metric Learning
Frontiers in Physiology, 2021 Remote ECG diagnosis has been widely used in the clinical ECG workflow. Especially for patients with pacemaker, in the limited information of patient's medical history, doctors need to determine whether the patient is wearing a pacemaker and also ...
Zhaoyang Ge +9 more
doaj +1 more source
Object Tracking With Structured Metric Learning
IEEE Access, 2019 In this paper, we propose a novel tracking method based on structured metric learning, which takes the advantages of both structured learning and distance metric learning.
Xiaolin Zhao +4 more
doaj +1 more source
metric-learn: Metric Learning Algorithms in Python
CoRR, 2019 metric-learn is an open source Python package implementing supervised and weakly-supervised distance metric learning algorithms. As part of scikit-learn-contrib, it provides a unified interface compatible with scikit-learn which allows to easily perform cross-validation, model selection, and pipelining with other machine learning estimators.
de Vazelhes, William +4 more
openaire +5 more sources
IEEE Access, 2021 Many object re-identification (Re-ID) methods that depend on large-scale training datasets have been proposed in recent years. However, the performance of these methods degrades dramatically when insufficient training data are available.
Sheng-Hung Fan +3 more
doaj +1 more source
CoRR, 2019 Recent literature has shown that symbolic data, such as text and graphs, is often better represented by points on a curved manifold, rather than in Euclidean space. However, geometrical operations on manifolds are generally more complicated than in Euclidean space, and thus many techniques for processing and analysis taken for granted in Euclidean ...
Max Aalto, Nakul Verma
openaire +2 more sources
Ground Metric Learning on Graphs [PDF]
Journal of Mathematical Imaging and Vision, 2020 Optimal transport (OT) distances between probability distributions are parameterized by the ground metric they use between observations. Their relevance for real-life applications strongly hinges on whether that ground metric parameter is suitably chosen.
Heitz, Matthieu +4 more
openaire +3 more sources
Gong-kuang zidonghua, 2023 In the traditional personnel re-recognition method in coal mine underground based on metric learning, because metric learning ignores the absolute distance between positive and negative samples, the gradient of the loss function disappears or disperses ...
ZHANG Liya, WANG Yu, HAO Bonan
doaj +1 more source
Multi-Sensors System and Deep Learning Models for Object Tracking
Sensors, 2023 Autonomous navigation relies on the crucial aspect of perceiving the environment to ensure the safe navigation of an autonomous platform, taking into consideration surrounding objects and their potential movements. Consequently, a fundamental requirement
Ghina El Natour +2 more
doaj +1 more source
A Multi-Layer Feature Fusion Method for Few-Shot Image Classification
Sensors, 2023 In image classification, few-shot learning deals with recognizing visual categories from a few tagged examples. The degree of expressiveness of the encoded features in this scenario is a crucial question that needs to be addressed in the models being ...
Jacó C. Gomes +2 more
doaj +1 more source