482 citations · 744 across the 13 of their papers we have counts for
13 papers
Adding Chit-Chat to Enhance Task-Oriented Dialogues
Kai Sun, Seungwhan Moon, Paul Crook +7
Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e.g., booking hotels), open…
Information Seeking in the Spirit of Learning: a Dataset for Conversational Curiosity
Pedro Rodriguez, Paul Crook, Seungwhan Moon +1
Open-ended human learning and information-seeking are increasingly mediated by digital assistants. However, such systems often ignore the user's pre-existing knowledge. Assuming a…
Improving Native Ads CTR Prediction by Large Scale Event Embedding and Recurrent Networks
Mehul Parsana, Krishna Poola, Yajun Wang +1
Click through rate (CTR) prediction is very important for Native advertisement but also hard as there is no direct query intent. In this paper we propose a large-scale event embedd…
Automated Cloud Provisioning on AWS using Deep Reinforcement Learning
Zhiguang Wang, Chul Gwon, Tim Oates +1
As the use of cloud computing continues to rise, controlling cost becomes increasingly important. Yet there is evidence that 30\% - 45\% of cloud spend is wasted. Existing tools fo…
Diabetic Retinopathy Detection via Deep Convolutional Networks for Discriminative Localization and Visual Explanation
Zhiguang Wang, Jianbo Yang
We proposed a deep learning method for interpretable diabetic retinopathy (DR) detection. The visual-interpretable feature of the proposed method is achieved by adding the regressi…
Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline
Zhiguang Wang, Weizhong Yan, Tim Oates
We propose a simple but strong baseline for time series classification from scratch with deep neural networks. Our proposed baseline models are pure end-to-end without any heavy pr…
Representation Learning with Deconvolution for Multivariate Time Series Classification and Visualization
Zhiguang Wang, Wei Song, Lu Liu +5
We propose a new model based on the deconvolutional networks and SAX discretization to learn the representation for multivariate time series. Deconvolutional networks fully exploit…
Encoding Temporal Markov Dynamics in Graph for Visualizing and Mining Time Series
Lu Liu, Zhiguang Wang
Time series and signals are attracting more attention across statistics, machine learning and pattern recognition as it appears widely in the industry especially in sensor and IoT…
Adopting Robustness and Optimality in Fitting and Learning
Zhiguang Wang, Tim Oates, James Lo
We generalized a modified exponentialized estimator by pushing the robust-optimal (RO) index to for achieving robustness to outliers by optimizing a quasi-Minimin fun…
Spatially Encoding Temporal Correlations to Classify Temporal Data Using Convolutional Neural Networks
Zhiguang Wang, Tim Oates
We propose an off-line approach to explicitly encode temporal patterns spatially as different types of images, namely, Gramian Angular Fields and Markov Transition Fields. This ena…
Empirical Studies on Symbolic Aggregation Approximation Under Statistical Perspectives for Knowledge Discovery in Time Series
Wei Song, Zhiguang Wang, Yangdong Ye +1
Symbolic Aggregation approXimation (SAX) has been the de facto standard representation methods for knowledge discovery in time series on a number of tasks and applications. So far,…
Adaptive Normalized Risk-Averting Training For Deep Neural Networks
Zhiguang Wang, Tim Oates, James Lo
This paper proposes a set of new error criteria and learning approaches, Adaptive Normalized Risk-Averting Training (ANRAT), to attack the non-convex optimization problem in traini…
Imaging Time-Series to Improve Classification and Imputation
Zhiguang Wang, Tim Oates
Inspired by recent successes of deep learning in computer vision, we propose a novel framework for encoding time series as different types of images, namely, Gramian Angular Summat…