no code implementations • 5 Jan 2024 • Parvin Malekzadeh, Ming Hou, Konstantinos N. Plataniotis
In this paper, we propose an algorithm that clarifies the theoretical connection between aleatory and epistemic uncertainty, unifies aleatory and epistemic uncertainty estimation, and quantifies the combined effect of both uncertainties for a risk-sensitive exploration.
no code implementations • 16 Oct 2023 • Parvin Malekzadeh, Ming Hou, Konstantinos N. Plataniotis
Putting together two ideas of hybrid model-based successor feature (MB-SF) and uncertainty leads to an approach to the problem of sample efficient uncertainty-aware knowledge transfer across tasks with different transition dynamics or/and reward functions.
no code implementations • 27 Oct 2022 • Zohreh Hajiakhondi-Meybodi, Arash Mohammadi, Ming Hou, Jamshid Abouei, Konstantinos N. Plataniotis
Followed by a Cross Attention (CA) module as the Fusion Center (FC), the proposed ViT-CAT is capable of learning the mutual information between temporal and spatial correlations, as well, resulting in improving the classification accuracy, and decreasing the model's complexity about 8 times.
no code implementations • 12 Oct 2022 • Zohreh Hajiakhondi-Meybodi, Arash Mohammadi, Ming Hou, Elahe Rahimian, Shahin Heidarian, Jamshid Abouei, Konstantinos N. Plataniotis
Most existing datadriven popularity prediction models, however, are not suitable for the coded/uncoded content placement frameworks.
no code implementations • 6 May 2022 • Zohreh Hajiakhondi-Meybodi, Ming Hou, Arash Mohammadi
Performance of UWB-based localization systems, however, can significantly degrade because of Non Line of Sight (NLoS) connections between a mobile user and UWB beacons.
no code implementations • 31 Mar 2022 • Parvin Malekzadeh, Mohammad Salimibeni, Ming Hou, Arash Mohammadi, Konstantinos N. Plataniotis
Recent studies in neuroscience suggest that Successor Representation (SR)-based models provide adaptation to changes in the goal locations or reward function faster than model-free algorithms, together with lower computational cost compared to that of model-based algorithms.
no code implementations • 24 Aug 2021 • Zohreh Hajiakhondi-Meybodi, Arash Mohammadi, Ming Hou, Konstantinos N. Plataniotis
Although UWB technology can enhance the accuracy of indoor positioning due to the use of a wide-frequency spectrum, there are key challenges ahead for its efficient implementation.
no code implementations • 11 Feb 2021 • Yingxu Wang, Fakhri Karray, Sam Kwong, Konstantinos N. Plataniotis, Henry Leung, Ming Hou, Edward Tunstel, Imre J. Rudas, Ljiljana Trajkovic, Okyay Kaynak, Janusz Kacprzyk, Mengchu Zhou, Michael H. Smith, Philip Chen, Shushma Patel
Symbiotic Autonomous Systems (SAS) are advanced intelligent and cognitive systems exhibiting autonomous collective intelligence enabled by coherent symbiosis of human-machine interactions in hybrid societies.
no code implementations • 28 Jul 2020 • Kenneth Lai, Helder C. R. Oliveira, Ming Hou, Svetlana N. Yanushkevich, Vlad Shmerko
An example of such a system is a cognitive biometric-enabled security checkpoint.
no code implementations • NeurIPS 2019 • Ming Hou, Jiajia Tang, Jianhai Zhang, Wanzeng Kong, Qibin Zhao
Tensor-based multimodal fusion techniques have exhibited great predictive performance.
no code implementations • ICLR 2019 • Xinqi Chen, Ming Hou, Guoxu Zhou, Qibin Zhao
Recent deep multi-task learning (MTL) has been witnessed its success in alleviating data scarcity of some task by utilizing domain-specific knowledge from related tasks.
no code implementations • 31 Oct 2018 • Chao Li, Zhun Sun, Jinshi Yu, Ming Hou, Qibin Zhao
We demonstrate this by compressing the convolutional layers via randomly-shuffled tensor decomposition (RsTD) for a standard classification task using CIFAR-10.
no code implementations • CVPR 2018 • Da Pan, Ping Shi, Ming Hou, Zefeng Ying, Sizhe Fu, Yuan Zhang
A key problem in blind image quality assessment (BIQA) is how to effectively model the properties of human visual system in a data-driven manner.
no code implementations • 21 Nov 2017 • Ming Hou, Brahim Chaib-Draa, Chao Li, Qibin Zhao
However, given limited P data, the conventional PU models tend to suffer from overfitting when adapted to very flexible deep neural networks.