Results 271 to 280 of about 7,006,651 (299)
Some of the next articles are maybe not open access.
Reinforcement learning based metric filtering for evolutionary distance metric learning
Intelligent Data Analysis, 2020Data collection plays an important role in business agility; data can prove valuable and provide insights for important features. However, conventional data collection methods can be costly and time-consuming. This paper proposes a hybrid system R-EDML that combines a sequential feature selection performed by Reinforcement Learning (RL) with the ...
Bassel Ali +4 more
openaire +2 more sources
Metric Learning for Image Alignment
International Journal of Computer Vision, 2009zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Minh Hoai Nguyen, Fernando De la Torre
openaire +3 more sources
Deep Adversarial Metric Learning
IEEE Transactions on Image Processing, 2020Learning an effective distance measurement between sample pairs plays an important role in visual analysis, where the training procedure largely relies on hard negative samples. However, hard negative samples usually account for the tiny minority in the training set, which may fail to fully describe the data distribution close to the decision boundary.
Yueqi Duan +3 more
openaire +3 more sources
Metric learning for reinforcement learning agents
International Joint Conference on Autonomous Agents and Multiagent Systems, 2011A key component of any reinforcement learning algorithm is the underlying representation used by the agent. While reinforcement learning (RL) agents have typically relied on hand-coded state representations, there has been a growing interest in learning this representation.
Matthew E. Taylor, Brian Kulis, Fei Sha
openaire +2 more sources
Learning a Metric for Code Readability
IEEE Transactions on Software Engineering, 2010In this paper, we explore the concept of code readability and investigate its relation to software quality. With data collected from 120 human annotators, we derive associations between a simple set of local code features and human notions of readability.
Raymond P. L. Buse, Westley Weimer
openaire +1 more source
Regression-based metric learning
2016 23rd International Conference on Pattern Recognition (ICPR), 2016Existing distance metric learning methods define an objective function and seek a distance metric (or equivalently a projection) that minimizes it. In this paper, we propose a different approach that illustrates how to formulate distance metric learning as a regression problem. First, the objective function is minimized to learn target representations.
Panagiotis Moutafis +2 more
openaire +1 more source
Learning multiple metrics for ranking
Frontiers of Computer Science in China, 2011zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Xiubo Geng, Xueqi Cheng
openaire +1 more source
Broad Metric Learning: A Fast and Efficient Discriminative Metric Learning Model
IEEE Transactions on CyberneticsMetric learning aims to learn a discriminative metric space, where samples of the same class stay close, and those of different classes far apart. Existing classical metric learning methods based on linear transformation have limited learning performance due to the low representation capability.
Xiaoman Hu +2 more
openaire +2 more sources
Multi-metric learning by a pair of twin-metric learning framework
Applied Intelligence, 2022Min Zhang +3 more
openaire +2 more sources
Machine Learning in Epigenetic Diseases
Medical Epigenetics, 2021Robert E Akins, Karyn Robinson
exaly