Search Results for author: Wei Pan

Found 59 papers, 15 papers with code

融合自编码器和对抗训练的中文新词发现方法(Finding Chinese New Word By Combining Self-encoder and Adversarial Training)

no code implementations CCL 2021 Wei Pan, Tianyuan Liu, Yuqing Sun, Bin Gong, Yongman Zhang, Ping Yang

“新词的不断涌现是语言的自然规律, 如在专业领域中新概念和实体名称代表了专业领域中某些共同特征集合的抽象概括, 经常作为关键词在句子中承担一定的角色。新词发现问题直接影响中文分词结果和后继文本语义理解任务的性能, 是自然语言处理研究领域的重要任务。本文提出了融合自编码器和对抗训练的中文新词发现模型, 采用字符级别的自编码器和无监督自学习的方式进行预训练, 可以有效提取语义信息, 不受分词结果影响, 适用于不同领域的文本;同时为了引入通用语言学知识, 添加了先验句法分析结果, 借助领域共享编码器融合语义和语法信息, 以提升划分歧义词的准确性;采用对抗训练机制, 以提取领域无关特征, 减少对于人工标注语料的依赖。实验选择六个不同的专业领域数据集评估新词发现任务, 结果显示本文模型优于其他现有方法;结合模型析构实验, 详细验证了各个模块的有效性。同时通过选择不同类型的源域数据和不同数量的目标域数据进行对比实验, 验证了模型的鲁棒性。最后以可视化的方式对比了自编码器和共享编码器对不同领域数据的编码结果, 显示了对抗训练方法能够有效地提取两者之间的相关性和差异性信息。”

Fault Detection and Tolerant Control for Aero2 2D0F Two-rotor Helicopter

no code implementations14 Mar 2024 Khalid Kabir Dandago, Long Zhang, Wei Pan

Stability and satisfactory performance are critical control requirements for Unmanned Aerial Vehicle (UAV) applications.

Fault Detection

Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control

1 code implementation27 Feb 2024 Wenhan Cao, Wei Pan

We prove that the local convergence rates for IntRL using the trapezoidal rule and Bayesian quadrature with a Mat\'ern kernel to be $O(N^{-2})$ and $O(N^{-b})$, where $N$ is the number of evenly-spaced samples and $b$ is the Mat\'ern kernel's smoothness parameter.

Open Ad Hoc Teamwork with Cooperative Game Theory

no code implementations23 Feb 2024 Jianhong Wang, Yang Li, Yuan Zhang, Wei Pan, Samuel Kaski

Open ad hoc teamwork further complicates this challenge by considering environments with a changing number of teammates, referred to as open teams.

Aligning Individual and Collective Objectives in Multi-Agent Cooperation

no code implementations19 Feb 2024 Yang Li, WenHao Zhang, Jianhong Wang, Shao Zhang, Yali Du, Ying Wen, Wei Pan

The visualization of learning dynamics effectively demonstrates that AgA successfully achieves alignment between individual and collective objectives.


NiSNN-A: Non-iterative Spiking Neural Networks with Attention with Application to Motor Imagery EEG Classification

no code implementations9 Dec 2023 Chuhan Zhang, Wei Pan, Cosimo Della Santina

Motor imagery, an important category in electroencephalogram (EEG) research, often intersects with scenarios demanding low energy consumption, such as portable medical devices and isolated environment operations.

EEG Motor Imagery

Deep Bayesian Reinforcement Learning for Spacecraft Proximity Maneuvers and Docking

no code implementations7 Nov 2023 Desong Du, Naiming Qi, Yanfang Liu, Wei Pan

This innovative approach allows the state-value function to be expressed as a Lyapunov function, leveraging the Gaussian process and deep kernel learning.


Causal Discovery with Generalized Linear Models through Peeling Algorithms

no code implementations25 Oct 2023 Minjie Wang, Xiaotong Shen, Wei Pan

This article presents a novel method for causal discovery with generalized structural equation models suited for analyzing diverse types of outcomes, including discrete, continuous, and mixed data.

Causal Discovery valid

Cross-Utterance Conditioned VAE for Speech Generation

no code implementations8 Sep 2023 Yang Li, Cheng Yu, Guangzhi Sun, Weiqin Zu, Zheng Tian, Ying Wen, Wei Pan, Chao Zhang, Jun Wang, Yang Yang, Fanglei Sun

Experimental results on the LibriTTS datasets demonstrate that our proposed models significantly enhance speech synthesis and editing, producing more natural and expressive speech.

Speech Synthesis

Few shot font generation via transferring similarity guided global style and quantization local style

1 code implementation ICCV 2023 Wei Pan, Anna Zhu, Xinyu Zhou, Brian Kenji Iwana, Shilin Li

To better capture the local styles, a cross-attention-based style transfer module is adopted to transfer the styles of reference glyphs to the components, where the components are self-learned discrete latent codes through vector quantization without manual definition.

Disentanglement Font Generation +2

JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games

no code implementations9 Aug 2023 Yang Li, Kun Xiong, Yingping Zhang, Jiangcheng Zhu, Stephen Mcaleer, Wei Pan, Jun Wang, Zonghong Dai, Yaodong Yang

This paper presents an empirical exploration of non-transitivity in perfect-information games, specifically focusing on Xiangqi, a traditional Chinese board game comparable in game-tree complexity to chess and shogi.

Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination

1 code implementation5 Jun 2023 Yang Li, Shao Zhang, Jichen Sun, WenHao Zhang, Yali Du, Ying Wen, Xinbing Wang, Wei Pan

In order to solve cooperative incompatibility in learning and effectively address the problem in the context of ZSC, we introduce the Cooperative Open-ended LEarning (COLE) framework, which formulates open-ended objectives in cooperative games with two players using perspectives of graph theory to evaluate and pinpoint the cooperative capacity of each strategy.

Weighted Point Cloud Normal Estimation

no code implementations6 May 2023 Weijia Wang, Xuequan Lu, Di Shao, Xiao Liu, Richard Dazeley, Antonio Robles-Kelly, Wei Pan

Existing normal estimation methods for point clouds are often less robust to severe noise and complex geometric structures.

Contrastive Learning regression

Cooperative Open-ended Learning Framework for Zero-shot Coordination

1 code implementation9 Feb 2023 Yang Li, Shao Zhang, Jichen Sun, Yali Du, Ying Wen, Xinbing Wang, Wei Pan

However, these approaches can result in a loss of learning and an inability to cooperate with certain strategies within the population, known as cooperative incompatibility.

Millimeter-level Resolution Photonic Multiband Radar Using a Single MZM and Sub-GHz-Bandwidth Electronics

no code implementations18 Oct 2022 Peixuan Li, Wenlin Bai, Xihua Zou, Ningyuan Zhong, Wei Pan, Lianshan Yan

We here propose a novel cost-effective millimeter-level resolution photonic multiband radar system using a single MZM driven by a 1-GHz-bandwidth LFM signal.

Deep Koopman Learning of Nonlinear Time-Varying Systems

no code implementations12 Oct 2022 Wenjian Hao, Bowen Huang, Wei Pan, Di wu, Shaoshuai Mou

This paper presents a data-driven approach to approximate the dynamics of a nonlinear time-varying system (NTVS) by a linear time-varying system (LTVS), which is resulted from the Koopman operator and deep neural networks.

Computational Efficiency

Cost-effective photonic super-resolution millimeter-wave joint radar-communication system using self-coherent detection

no code implementations9 Oct 2022 Wenlin Bai, Peixuan Li, Xihua Zou, Ningyuan Zhong, Wei Pan, Lianshan Yan, Bin Luo

Then the self-coherent detection, as a simple and low-cost means, is accordingly facilitated for both de-chirping of MMW radar and frequency down-conversion reception of MMW communication, which circumvents the costly high-speed mixers along with MMW local oscillators and more significantly achieves the real-time decomposition of radar and communication information.

Joint Radar-Communication Super-Resolution

Robust Bayesian Inference for Moving Horizon Estimation

no code implementations5 Oct 2022 Wenhan Cao, Chang Liu, Zhiqian Lan, Shengbo Eben Li, Wei Pan, Angelo Alessandri

The accuracy of moving horizon estimation (MHE) suffers significantly in the presence of measurement outliers.

Bayesian Inference Combinatorial Optimization

Bayesian Learning to Discover Mathematical Operations in Governing Equations of Dynamic Systems

1 code implementation1 Jun 2022 Hongpeng Zhou, Wei Pan

Discovering governing equations from data is critical for diverse scientific disciplines as they can provide insights into the underlying phenomenon of dynamic systems.

AI-enabled Automatic Multimodal Fusion of Cone-Beam CT and Intraoral Scans for Intelligent 3D Tooth-Bone Reconstruction and Clinical Applications

no code implementations11 Mar 2022 Jin Hao, Jiaxiang Liu, Jin Li, Wei Pan, Ruizhe Chen, Huimin Xiong, Kaiwei Sun, Hangzheng Lin, Wanlu Liu, Wanghui Ding, Jianfei Yang, Haoji Hu, Yueling Zhang, Yang Feng, Zeyu Zhao, Huikai Wu, Youyi Zheng, Bing Fang, Zuozhu Liu, Zhihe Zhao

Here, we present a Deep Dental Multimodal Analysis (DDMA) framework consisting of a CBCT segmentation model, an intraoral scan (IOS) segmentation model (the most accurate digital dental model), and a fusion model to generate 3D fused crown-root-bone structures with high fidelity and accurate occlusal and dentition information.


Towards Uniform Point Distribution in Feature-preserving Point Cloud Filtering

no code implementations5 Jan 2022 Shuaijun Chen, Jinxi Wang, Wei Pan, Shang Gao, Meili Wang, Xuequan Lu

As a popular representation of 3D data, point cloud may contain noise and need to be filtered before use.

Two-level monotonic multistage recommender systems

no code implementations6 Oct 2021 Ben Dai, Xiaotong Shen, Wei Pan

In this article, we develop a multistage recommender system utilizing a two-level monotonic property characterizing a monotonic chain of events for personalized prediction.

Recommendation Systems Vocal Bursts Valence Prediction

Robust Tube-based Model Predictive Control with Koopman Operators--Extended Version

no code implementations30 Aug 2021 Xinglong Zhang, Wei Pan, Riccardo Scattolini, Shuyou Yu, Xin Xu

The finite data-driven approximation of Koopman operators results in a class of linear predictors, useful for formulating linear model predictive control (MPC) of nonlinear dynamical systems with reduced computational complexity.

Model Predictive Control

Sparse Bayesian Deep Learning for Dynamic System Identification

1 code implementation27 Jul 2021 Hongpeng Zhou, Chahine Ibrahim, Wei Xing Zheng, Wei Pan

Furthermore, a practical calculation approach based on the Monte-Carlo integration method is derived to quantify the uncertainty of the parameters and predictions.

Uncertainty Quantification

Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning

1 code implementation19 Apr 2021 Jie Ren, Yewen Li, Zihan Ding, Wei Pan, Hao Dong

However, grasping distinguishable skills for some tasks with non-unique optima can be essential for further improving its learning efficiency and performance, which may lead to a multimodal policy represented as a mixture-of-experts (MOE).

reinforcement-learning Reinforcement Learning (RL)

Reinforcement Learning for Orientation Estimation Using Inertial Sensors with Performance Guarantee

no code implementations3 Mar 2021 Liang Hu, Yujie Tang, Zhipeng Zhou, Wei Pan

This paper presents a deep reinforcement learning (DRL) algorithm for orientation estimation using inertial sensors combined with magnetometer.

reinforcement-learning Reinforcement Learning (RL)

Significance tests of feature relevance for a black-box learner

1 code implementation2 Mar 2021 Ben Dai, Xiaotong Shen, Wei Pan

In this article, we derive one-split and two-split tests relaxing the assumptions and computational complexity of existing black-box tests and extending to examine the significance of a collection of features of interest in a dataset of possibly a complex type such as an image.

Decision Making

Reinforcement Learning for Control with Probabilistic Stability Guarantee

no code implementations1 Jan 2021 Minghao Han, Zhipeng Zhou, Lixian Zhang, Jun Wang, Wei Pan

Reinforcement learning is promising to control dynamical systems for which the traditional control methods are hardly applicable.

reinforcement-learning Reinforcement Learning (RL)

Adaptive Deep Learning for Entity Resolution by Risk Analysis

no code implementations7 Dec 2020 Zhaoqiang Chen, Qun Chen, Youcef Nafa, Tianyi Duan, Wei Pan, Lijun Zhang, Zhanhuai Li

Built on the recent advances on risk analysis for ER, the proposed approach first trains a deep model on labeled training data, and then fine-tunes it by minimizing its estimated misprediction risk on unlabeled target data.

Entity Resolution Transfer Learning

Lyapunov-Based Reinforcement Learning State Estimator

no code implementations26 Oct 2020 Liang Hu, ChengWei Wu, Wei Pan

An actor-critic reinforcement learning algorithm is proposed to learn the state estimator approximated by a deep neural network.

reinforcement-learning Reinforcement Learning (RL)

Penalized model-based clustering of fMRI data

no code implementations13 Oct 2020 Andrew DiLernia, Karina Quevedo, Jazmin Camchong, Kelvin Lim, Wei Pan, Lin Zhang

To this end, we propose a random covariance clustering model (RCCM) to concurrently cluster subjects based on their FC networks, estimate the unique FC networks of each subject, and to infer shared network features.


Lyapunov-Based Reinforcement Learning for Decentralized Multi-Agent Control

no code implementations20 Sep 2020 Qingrui Zhang, Hao Dong, Wei Pan

More importantly, the existing multi-agent reinforcement learning (MARL) algorithms cannot ensure the closed-loop stability of a multi-agent system from a control-theoretic perspective, so the learned control polices are highly possible to generate abnormal or dangerous behaviors in real applications.

Multi-agent Reinforcement Learning reinforcement-learning +1

Model-Reference Reinforcement Learning for Collision-Free Tracking Control of Autonomous Surface Vehicles

no code implementations17 Aug 2020 Qingrui Zhang, Wei Pan, Vasso Reppa

This paper presents a novel model-reference reinforcement learning algorithm for the intelligent tracking control of uncertain autonomous surface vehicles with collision avoidance.

Collision Avoidance reinforcement-learning +1

Towards Lossless Binary Convolutional Neural Networks Using Piecewise Approximation

no code implementations8 Aug 2020 Baozhou Zhu, Zaid Al-Ars, Wei Pan

Binary Convolutional Neural Networks (CNNs) can significantly reduce the number of arithmetic operations and the size of memory storage, which makes the deployment of CNNs on mobile or embedded systems more promising.


Stochastic mesoscale circulation dynamics in the thermal ocean

no code implementations10 Jun 2020 Darryl D. Holm, Erwin Luesink, Wei Pan

Asymptotic expansion of the TRSW model equations in these three small parameters leads to the deterministic thermal versions of the Salmon's L1 (TL1) model and the thermal quasi-geostrophic (TQG) model, upon expanding in the neighbourhood of thermal quasi-geostrophic balance among the flow velocity and the gradients of free surface elevation and buoyancy.

Fluid Dynamics Geophysics

Actor-Critic Reinforcement Learning for Control with Stability Guarantee

no code implementations29 Apr 2020 Minghao Han, Lixian Zhang, Jun Wang, Wei Pan

Reinforcement Learning (RL) and its integration with deep learning have achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation.

Motion Planning reinforcement-learning +1

Model-Reference Reinforcement Learning Control of Autonomous Surface Vehicles with Uncertainties

no code implementations30 Mar 2020 Qingrui Zhang, Wei Pan, Vasso Reppa

With the conventional control, we can ensure the learning-based control law provides closed-loop stability for the overall system, and potentially increase the sample efficiency of the deep reinforcement learning.

Autonomous Vehicles reinforcement-learning +1

A Sparse Bayesian Deep Learning Approach for Identification of Cascaded Tanks Benchmark

no code implementations15 Nov 2019 Hongpeng Zhou, Chahine Ibrahim, Wei Pan

This raises the challenge that how to train a neural network for system identification with a small dataset.

$H_\infty$ Model-free Reinforcement Learning with Robust Stability Guarantee

1 code implementation7 Nov 2019 Minghao Han, Yuan Tian, Lixian Zhang, Jun Wang, Wei Pan

In this paper, we introduce and extend the idea of robust stability and $H_\infty$ control to design policies with both stability and robustness guarantee.

Autonomous Driving reinforcement-learning +2

Variational Constrained Reinforcement Learning with Application to Planning at Roundabout

no code implementations25 Sep 2019 Yuan Tian, Minghao Han, Lixian Zhang, Wulong Liu, Jun Wang, Wei Pan

In this paper, we combine variational learning and constrained reinforcement learning to simultaneously learn a Conditional Representation Model (CRM) to encode the states into safe and unsafe distributions respectively as well as to learn the corresponding safe policy.

Autonomous Driving reinforcement-learning +1

Model-free Learning Control of Nonlinear Stochastic Systems with Stability Guarantee

no code implementations25 Sep 2019 Minghao Han, Yuan Tian, Lixian Zhang, Jun Wang, Wei Pan

Reinforcement learning (RL) offers a principled way to achieve the optimal cumulative performance index in discrete-time nonlinear stochastic systems, which are modeled as Markov decision processes.

Continuous Control Open-Ended Question Answering +1

BayesNAS: A Bayesian Approach for Neural Architecture Search

no code implementations13 May 2019 Hongpeng Zhou, Minghao Yang, Jun Wang, Wei Pan

One-Shot Neural Architecture Search (NAS) is a promising method to significantly reduce search time without any separate training.

Neural Architecture Search

HLO: Half-kernel Laplacian Operator for Surface Smoothing

1 code implementation12 May 2019 Wei Pan, Xuequan Lu, Yuanhao Gong, Wenming Tang, Jun Liu, Ying He, Guoping Qiu

This paper presents a simple yet effective method for feature-preserving surface smoothing.

Computational Geometry Graphics

Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning

no code implementations ICLR 2019 Ying Wen, Yaodong Yang, Rui Luo, Jun Wang, Wei Pan

Our methods are tested on both the matrix game and the differential game, which have a non-trivial equilibrium where common gradient-based methods fail to converge.

Multi-agent Reinforcement Learning reinforcement-learning +1

Deep Learning Hyperspectral Image Classification Using Multiple Class-based Denoising Autoencoders, Mixed Pixel Training Augmentation, and Morphological Operations

no code implementations11 Jul 2018 Ball John E., Wei Pan

Herein, we present a system for hyperspectral image segmentation that utilizes multiple class--based denoising autoencoders which are efficiently trained.

Data Augmentation Denoising +4

LiDAR and Camera Detection Fusion in a Real Time Industrial Multi-Sensor Collision Avoidance System

no code implementations11 Jul 2018 Wei Pan, Cagle Lucas, Reza Tasmia, Ball John, Gafford James

Collision avoidance is a critical task in many applications, such as ADAS (advanced driver-assistance systems), industrial automation and robotics.

Collision Avoidance Model Predictive Control

Towards Accurate Binary Convolutional Neural Network

2 code implementations NeurIPS 2017 Xiaofan Lin, Cong Zhao, Wei Pan

We introduce a novel scheme to train binary convolutional neural networks (CNNs) -- CNNs with weights and activations constrained to {-1,+1} at run-time.

Mixed Neural Network Approach for Temporal Sleep Stage Classification

no code implementations15 Oct 2016 Hao Dong, Akara Supratak, Wei Pan, Chao Wu, Paul M. Matthews, Yike Guo

Use of this recording configuration with neural network deconvolution promises to make clinically indicated home sleep studies practical.

Classification EEG +1

Human collective intelligence as distributed Bayesian inference

no code implementations5 Aug 2016 Peter M. Krafft, Julia Zheng, Wei Pan, Nicolás Della Penna, Yaniv Altshuler, Erez Shmueli, Joshua B. Tenenbaum, Alex Pentland

To address this gap, we introduce a new analytical framework: We propose that groups arrive at accurate shared beliefs via distributed Bayesian inference.

Bayesian Inference Decision Making +1

DropNeuron: Simplifying the Structure of Deep Neural Networks

1 code implementation23 Jun 2016 Wei Pan, Hao Dong, Yike Guo

We proposed regularisers which support a simple mechanism of dropping neurons during a network training process.

Distributed Reconstruction of Nonlinear Networks: An ADMM Approach

no code implementations28 Mar 2014 Wei Pan, Aivar Sootla, Guy-Bart Stan

In this paper, we present a distributed algorithm for the reconstruction of large-scale nonlinear networks.

Time Series Time Series Analysis

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