Results 21 to 30 of about 2,763,116 (335)
Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach [PDF]
Computer Vision and Pattern Recognition, 2016 We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and network ...
Giorgio Patrini +4 more
semanticscholar +1 more source
2020 IEEE International Symposium on Information Theory (ISIT), 2020 We introduce Noise Recycling, a method that substantially enhances decoding performance of orthogonal channels subject to correlated noise without the need for joint encoding or decoding. The method can be used with any combination of codes, code-rates and decoding techniques.
Cohen, Alejandro +3 more
openaire +7 more sources
Design and testing of a smart rubber stave for marine water-lubricated bearings
Science and Engineering of Composite Materials, 2022 The water-lubricated bearing is mainly installed at the stern of the ship to support the rotation of the main shaft of the ship, which is an important component of the ship’s power plant.
Yu Xiao-feng +5 more
doaj +1 more source
Calibrating Noise to Sensitivity in Private Data Analysis
Theory of Cryptography Conference, 2006 We continue a line of research initiated in [10, 11] on privacy-preserving statistical databases. Consider a trusted server that holds a database of sensitive information.
C. Dwork +3 more
semanticscholar +1 more source
Research on structural sound source localization method by neural network
EURASIP Journal on Advances in Signal Processing, 2023 To solve problems related to much calculation to adapt to complex scenes in traditional structural sound source localization, this paper proposes a method based on neural network.
Xiufeng Huang +3 more
doaj +1 more source
Probabilistic End-To-End Noise Correction for Learning With Noisy Labels [PDF]
Computer Vision and Pattern Recognition, 2019 Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with noisy labels, but such noise makes networks overfit seriously and ...
Kun Yi, Jianxin Wu
semanticscholar +1 more source
Robust Loss Functions under Label Noise for Deep Neural Networks [PDF]
AAAI Conference on Artificial Intelligence, 2017 In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant.
Aritra Ghosh, Himanshu Kumar, P. Sastry
semanticscholar +1 more source
Journal of Economic Theory, 2013 We study the attitude of decision makers to skewed noise. For a binary lottery that yields the better outcome with probability p, we identify noise around p with a compound lottery that induces a distribution over the exact value of the probability and has an average value p.
David Dillenberger, Uzi Segal
openaire +4 more sources
Performance research and safety verification of compound structure air spring
Advances in Mechanical Engineering, 2020 To further reduce the vertical stiffness of the air spring, appropriately reduce its lateral stiffness to attenuate the transmission of vibration along the lateral and longitudinal directions, a compound structure air spring (CSAS) was designed.
Lihang Yin +4 more
doaj +1 more source