11 citations · 11 across the 2 of their papers we have counts for
6 papers
Sig-Wasserstein GANs for Time Series Generation
Hao Ni, Lukasz Szpruch, Marc Sabate-Vidales +3
Synthetic data is an emerging technology that can significantly accelerate the development and deployment of AI machine learning pipelines. In this work, we develop high-fidelity t…
Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition
Shujian Liao, Terry Lyons, Weixin Yang +2
This paper contributes to the challenge of skeleton-based human action recognition in videos. The key step is to develop a generic network architecture to extract discriminative fe…
An efficient representation of chronological events in medical texts
Andrey Kormilitzin, Nemanja Vaci, Qiang Liu +3
In this work we addressed the problem of capturing sequential information contained in longitudinal electronic health records (EHRs). Clinical notes, which is a particular type of…
Signature features with the visibility transformation
Yue Wu, Hao Ni, Terence J. Lyons +1
In this paper we put the visibility transformation on a clear theoretical footing and show that this transform is able to embed the effect of the absolute position of the data stre…
Learning stochastic differential equations using RNN with log signature features
Shujian Liao, Terry Lyons, Weixin Yang +1
This paper contributes to the challenge of learning a function on streamed multimodal data through evaluation. The core of the result of our paper is the combination of two quite d…
Cascading Bandits for Large-Scale Recommendation Problems
Shi Zong, Hao Ni, Kenny Sung +3
Most recommender systems recommend a list of items. The user examines the list, from the first item to the last, and often chooses the first attractive item and does not examine th…