Results 281 to 290 of about 2,079,458 (324)

Transferred Feature Selection

2009 IEEE International Conference on Data Mining Workshops, 2009
Traditional feature selection algorithms require a large number of labeled training instances to find out the most informative subset of features. However, in many real-world applications, the labeled data are often difficult, expensive or time-consuming to obtain.
Wei Bi, Yuan Shi, Zhenzhong Lan
openaire   +1 more source

Transfer Reinforcement Learning: Feature Transferability in Ship Collision Avoidance

Volume 3B: 49th Design Automation Conference (DAC), 2023
Abstract The integration of artificial intelligence into engineering work has become increasingly prevalent. Engineering work processes can be highly complex, and learning from scratch requires large computation resources. Transfer learning has emerged as a promising technique for improving learning efficiency by leveraging knowledge ...
Xinrui Wang, Yan Jin
openaire   +1 more source

Hierarchical Energy-transfer Features

Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods, 2014
In the paper, we propose the novel and efficient object descriptors that are designed to describe the appearance of the objects. The descriptors are called as Hierarchical Energy-Transfer Features (HETF). The main idea behind HETF is that the shape of the objects can be described by the function of energy distribution.
openaire   +1 more source

Facial-Feature Resemblance Elicits the Transference Effect

Psychological Science, 2010
In transference, a perceiver’s representation of a significant other is activated and used to interpret and respond to a new target person who bears some resemblance to the particular significant other. Integrating research on face perception and transference, we hypothesized that transference can occur on the basis of the resemblance of a target’s ...
Michael W, Kraus, Serena, Chen
openaire   +2 more sources

Features of writtenness transferred

2011
This paper emphasizes language contact situations in general as an origin of hybrid features of writtenness. Furthermore it stresses the necessity of taking into account the medial-conceptional differences between languages of distance (prototypically written) and languages of proximity (prototypically spoken) when analyzing language contact data and ...
openaire   +1 more source

Feature-based garment model transfer

2018
With the improvement of CAD/CG (computer-aided design and computer graphics) technology and the development of VR (virtual reality) and AR (augmented reality) techniques, more and more real-world items surrounding people have been digitalized and displayed in the virtual world as well as people themselves.
openaire   +2 more sources

Transfer Learning via Feature Isomorphism Discovery

Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018
Transfer learning has gained increasing attention due to the inferior performance of machine learning algorithms with insufficient training data. Most of the previous homogeneous or heterogeneous transfer learning works aim to learn a mapping function between feature spaces based on the inherent correspondence across the source and target domains or ...
Shimin Di, Jingshu Peng, Yanyan Shen, Lei Chen   +3 more
openaire   +1 more source

Boosting Online Feature Transfer via Separable Feature Fusion

2022 International Joint Conference on Neural Networks (IJCNN), 2022
Lujun Li, Shiuan-Ni Liang, Ya Yang, Zhe Jin   +3 more
openaire   +1 more source