Search Results for author: Zhiguang Wang

Found 20 papers, 13 papers with code

Taylor Genetic Programming for Symbolic Regression

no code implementations28 Apr 2022 Baihe He, Qiang Lu, Qingyun Yang, Jake Luo, Zhiguang Wang

So, the search process of GP is usually slow, and the final results could be unstable. To guide GP by these characteristics, we propose a new method for SR, called Taylor genetic programming (TaylorGP) (Code and appendix at https://kgae-cup. github. io/TaylorGP/).

Symbolic Regression

Exploring Hidden Semantics in Neural Networks with Symbolic Regression

no code implementations22 Apr 2022 Yuanzhen Luo, Qiang Lu, Xilei Hu, Jake Luo, Zhiguang Wang

It then leverages a multi-chromosome NNCGP to represent hidden semantics of all layers of the NN.

Symbolic Regression

Zero-Shot Dialogue State Tracking via Cross-Task Transfer

1 code implementation EMNLP 2021 Zhaojiang Lin, Bing Liu, Andrea Madotto, Seungwhan Moon, Paul Crook, Zhenpeng Zhou, Zhiguang Wang, Zhou Yu, Eunjoon Cho, Rajen Subba, Pascale Fung

Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data.

Dialogue State Tracking Question Answering +1

Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking

1 code implementation10 May 2021 Zhaojiang Lin, Bing Liu, Seungwhan Moon, Paul Crook, Zhenpeng Zhou, Zhiguang Wang, Zhou Yu, Andrea Madotto, Eunjoon Cho, Rajen Subba

Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data.

Dialogue State Tracking Transfer Learning

Gated Transformer Networks for Multivariate Time Series Classification

1 code implementation26 Mar 2021 Minghao Liu, Shengqi Ren, Siyuan Ma, Jiahui Jiao, Yizhou Chen, Zhiguang Wang, Wei Song

In this work, we explored a simple extension of the current Transformer Networks with gating, named Gated Transformer Networks (GTN) for the multivariate time series classification problem.

Classification General Classification +3

Continual Learning in Task-Oriented Dialogue Systems

1 code implementation EMNLP 2021 Andrea Madotto, Zhaojiang Lin, Zhenpeng Zhou, Seungwhan Moon, Paul Crook, Bing Liu, Zhou Yu, Eunjoon Cho, Zhiguang Wang

Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining.

Continual Learning Multi-Task Learning +2

Adding Chit-Chat to Enhance Task-Oriented Dialogues

1 code implementation NAACL 2021 Kai Sun, Seungwhan Moon, Paul Crook, Stephen Roller, Becka Silvert, Bing Liu, Zhiguang Wang, Honglei Liu, Eunjoon Cho, Claire Cardie

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-domain chatbots aim at making socially engaging conversations.

Dialogue Generation Dialogue Understanding +1

Information Seeking in the Spirit of Learning: a Dataset for Conversational Curiosity

1 code implementation EMNLP 2020 Pedro Rodriguez, Paul Crook, Seungwhan Moon, Zhiguang Wang

Assuming a correlation between engagement and user responses such as "liking" messages or asking followup questions, we design a Wizard-of-Oz dialog task that tests the hypothesis that engagement increases when users are presented with facts related to what they know.

Improving Native Ads CTR Prediction by Large Scale Event Embedding and Recurrent Networks

no code implementations24 Apr 2018 Mehul Parsana, Krishna Poola, Yajun Wang, Zhiguang Wang

The CTR prediction problem is modeled as a supervised recurrent neural network, which naturally model the user history as a sequence of events.

Click-Through Rate Prediction

Automated Cloud Provisioning on AWS using Deep Reinforcement Learning

1 code implementation13 Sep 2017 Zhiguang Wang, Chul Gwon, Tim Oates, Adam Iezzi

As the use of cloud computing continues to rise, controlling cost becomes increasingly important.

Q-Learning reinforcement-learning +1

Encoding Temporal Markov Dynamics in Graph for Visualizing and Mining Time Series

1 code implementation24 Oct 2016 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 related research and applications, but few advances has been achieved in effective time series visual analytics and interaction due to its temporal dimensionality and complex dynamics.

General Classification Time Series

Adopting Robustness and Optimality in Fitting and Learning

no code implementations13 Oct 2015 Zhiguang Wang, Tim Oates, James Lo

We generalized a modified exponentialized estimator by pushing the robust-optimal (RO) index $\lambda$ to $-\infty$ for achieving robustness to outliers by optimizing a quasi-Minimin function.

Spatially Encoding Temporal Correlations to Classify Temporal Data Using Convolutional Neural Networks

no code implementations24 Sep 2015 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.

Classification General Classification +1

Empirical Studies on Symbolic Aggregation Approximation Under Statistical Perspectives for Knowledge Discovery in Time Series

no code implementations8 Jun 2015 Wei Song, Zhiguang Wang, Yangdong Ye, Ming Fan

Our work provides an analytical framework with several statistical tools to analyze, evaluate and further improve the symbolic dynamics for knowledge discovery in time series.

Time Series

Adaptive Normalized Risk-Averting Training For Deep Neural Networks

no code implementations8 Jun 2015 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 training deep neural networks (DNNs).

Imaging Time-Series to Improve Classification and Imputation

3 code implementations1 Jun 2015 Zhiguang Wang, Tim Oates

We used Tiled Convolutional Neural Networks (tiled CNNs) on 20 standard datasets to learn high-level features from the individual and compound GASF-GADF-MTF images.

Classification General Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.