no code implementations • 24 Mar 2024 • Lijin Wu, Shanshan Lei, Feilong Liao, Yuanjun Zheng, Yuxin Liu, Wentao Fu, Hao Song, Jiajun Zhou
As the number of IoT devices increases, security concerns become more prominent.
no code implementations • 24 Mar 2024 • Hao Song, Jiacheng Yao, Zhengxi Li, Shaocong Xu, Shibo Jin, Jiajun Zhou, Chenbo Fu, Qi Xuan, Shanqing Yu
Additionally, for the privacy security of FLGNN, this paper designs membership inference attack experiments and differential privacy defense experiments.
no code implementations • 9 Feb 2024 • Hao Song, Wei Lin, Wei Song, Man Wang
To enhance precision and comprehensiveness in identifying targets in electric power construction monitoring video, a novel target recognition algorithm utilizing infrared imaging is explored.
no code implementations • 20 Dec 2021 • Telmo Silva Filho, Hao Song, Miquel Perello-Nieto, Raul Santos-Rodriguez, Meelis Kull, Peter Flach
This paper provides both an introduction to and a detailed overview of the principles and practice of classifier calibration.
no code implementations • 3 Nov 2021 • Hao Song, Lingjia Liu, Bodong Shang, Scott Pudlewski, Elizabeth Serena Bentley
When an unmanned aerial vehicle (UAV) network is utilized as an aerial small base station (BS), like a relay deployed far away from macro BSs, existing multicast methods based on acknowledgement (ACK) feedback and retransmissions may encounter severe delay and signaling overhead due to hostile wireless environments caused by a long-distance propagation and numerous UAVs.
no code implementations • 3 Jan 2020 • Pei Xu, Shan Huang, Hongzhen Wang, Hao Song, Shen Huang, Qi Ju
Chinese keyword spotting is a challenging task as there is no visual blank for Chinese words.
1 code implementation • NeurIPS 2019 • Meelis Kull, Miquel Perello Nieto, Markus Kängsepp, Telmo Silva Filho, Hao Song, Peter Flach
Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence.
3 code implementations • 28 Oct 2019 • Meelis Kull, Miquel Perello-Nieto, Markus Kängsepp, Telmo Silva Filho, Hao Song, Peter Flach
Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence.
1 code implementation • 7 Aug 2019 • Tom Diethe, Meelis Kull, Niall Twomey, Kacper Sokol, Hao Song, Miquel Perello-Nieto, Emma Tonkin, Peter Flach
This paper describes HyperStream, a large-scale, flexible and robust software package, written in the Python language, for processing streaming data with workflow creation capabilities.
no code implementations • 15 May 2019 • Hao Song, Tom Diethe, Meelis Kull, Peter Flach
We are concerned with obtaining well-calibrated output distributions from regression models.
no code implementations • 28 Oct 2018 • Hao-Hsuan Chang, Hao Song, Yang Yi, Jianzhong Zhang, Haibo He, Lingjia Liu
To be specific, we apply the powerful machine learning tool, deep reinforcement learning (DRL), for SUs to learn "appropriate" spectrum access strategies in a distributed fashion assuming NO knowledge of the underlying system statistics.
no code implementations • 20 Jun 2018 • Hao Song, Meelis Kull, Peter Flach
The task of calibration is to retrospectively adjust the outputs from a machine learning model to provide better probability estimates on the target variable.
1 code implementation • 9 Feb 2014 • Hao Song, Chun-Chung Chen, Jyh-Jang Sun, Pik-Yin Lai, C. K. Chan
Repeating patterns of spike sequences from a neuronal network have been proposed to be useful in the reconstruction of the network topology.
Neurons and Cognition