Zobrazeno 1 - 10
of 118
pro vyhledávání: '"Mengshoel, Ole J"'
Autor:
Chen, Jianpeng, Wang, Yujing, Zeng, Ming, Xiang, Zongyi, Hou, Bitan, Tong, Yunhai, Mengshoel, Ole J., Ren, Yazhou
Publikováno v:
Information Sciences 674 (2024): 120681
Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. However, because these traditional GNNs do not distinguish among various downstream tasks, embeddings embedded by them are not alway
Externí odkaz:
http://arxiv.org/abs/2106.10866
We propose a novel framework for structured bandits, which we call an influence diagram bandit. Our framework captures complex statistical dependencies between actions, latent variables, and observations; and thus unifies and extends many existing mo
Externí odkaz:
http://arxiv.org/abs/2007.04915
Autor:
Hou, Bitan, Wang, Yujing, Zeng, Ming, Jiang, Shan, Mengshoel, Ole J., Tong, Yunhai, Bai, Jing
Graph is a natural representation of data for a variety of real-word applications, such as knowledge graph mining, social network analysis and biological network comparison. For these applications, graph embedding is crucial as it provides vector rep
Externí odkaz:
http://arxiv.org/abs/1911.09454
Autor:
Lee, Ritchie, Mengshoel, Ole J., Saksena, Anshu, Gardner, Ryan, Genin, Daniel, Silbermann, Joshua, Owen, Michael, Kochenderfer, Mykel J.
Publikováno v:
Journal of Artificial Intelligence Research (JAIR) 69 (2020) 1165-1201
Finding the most likely path to a set of failure states is important to the analysis of safety-critical systems that operate over a sequence of time steps, such as aircraft collision avoidance systems and autonomous cars. In many applications such as
Externí odkaz:
http://arxiv.org/abs/1811.02188
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Zeng, Ming, Gao, Haoxiang, Yu, Tong, Mengshoel, Ole J., Langseth, Helge, Lane, Ian, Liu, Xiaobing
Publikováno v:
The International Symposium on Wearable Computers (ISWC) 2018
Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components, unimportant
Externí odkaz:
http://arxiv.org/abs/1810.04038
Random walk based distance measures for graphs such as commute-time distance are useful in a variety of graph algorithms, such as clustering, anomaly detection, and creating low dimensional embeddings. Since such measures hinge on the spectral decomp
Externí odkaz:
http://arxiv.org/abs/1802.05421
Labeled data used for training activity recognition classifiers are usually limited in terms of size and diversity. Thus, the learned model may not generalize well when used in real-world use cases. Semi-supervised learning augments labeled examples
Externí odkaz:
http://arxiv.org/abs/1801.07827
Dialog response selection is an important step towards natural response generation in conversational agents. Existing work on neural conversational models mainly focuses on offline supervised learning using a large set of context-response pairs. In t
Externí odkaz:
http://arxiv.org/abs/1711.08493
We study the problem of learning a latent variable model from a stream of data. Latent variable models are popular in practice because they can explain observed data in terms of unobserved concepts. These models have been traditionally studied in the
Externí odkaz:
http://arxiv.org/abs/1709.07172