Search Results for author:
Found 60 papers, 18 papers with code
糖尿病电子病历实体及关系标注语料库构建(Construction of Corpus for Entity and Relation Annotation of Diabetes Electronic Medical Records)
“电子病历是医疗信息的重要来源, 包含大量与医疗相关的领域知识。本文从糖尿病电子病历文本入手, 在调研了国内外已有的电子病历语料库的基础上, 参考坉圲坂圲实体及关系分类, 建立了糖尿病电子病历实体及实体关系分类体系, 并制定了标注规范。利用实体及关系标注平台, 进行了实体及关系预标注及多轮人工校对工作, 形成了糖尿病电子病历实体及关系标注语料库(Diabetes Electronic Medical Record entity and Related Corpus DEMRC)。所构建的DEMRC包含8899个实体、456个实体修饰及16564个关系。对DEMRC进行一致性评价和分析, 标注结果达到了较高的一致性。针对实体识别和实体关系抽取任务, 分别采用基于迁移学习的Bi-LSTM-CRF模型和RoBERTa模型进行初步实验, 并对语料库中的各类实体及关系进行评估, 为后续糖尿病电子病历实体识别及关系抽取研究以及糖尿病知识图谱构建打下基础。”
Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models.
A Unified Algebraic Perspective on Lipschitz Neural Networks
Important research efforts have focused on the design and training of neural networks with a controlled Lipschitz constant.
Multi-Feature Integration for Perception-Dependent Examination-Bias Estimation
Eliminating examination bias accurately is pivotal to apply click-through data to train an unbiased ranking model.
Pretraining De-Biased Language Model with Large-scale Click Logs for Document Ranking
Pre-trained language models have achieved great success in various large-scale information retrieval tasks.
Uniform tensor clustering by jointly exploring sample affinities of various orders
Conventional clustering methods based on pairwise affinity usually suffer from the concentration effect while processing huge dimensional features yet low sample sizes data, resulting in inaccuracy to encode the sample proximity and suboptimal performance in clustering.
Learning the Kalman Filter with Fine-Grained Sample Complexity
We develop the first end-to-end sample complexity of model-free policy gradient (PG) methods in discrete-time infinite-horizon Kalman filtering.
Global Convergence of Direct Policy Search for State-Feedback $\mathcal{H}_\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential
In this work, we show that direct policy search is guaranteed to find the global solution of the robust $\mathcal{H}_\infty$ state-feedback control design problem.
Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies
Gradient-based methods have been widely used for system design and optimization in diverse application domains.
Weight-based Channel-model Matrix Framework provides a reasonable solution for EEG-based cross-dataset emotion recognition
Cross-dataset emotion recognition as an extremely challenging task in the field of EEG-based affective computing is influenced by many factors, which makes the universal models yield unsatisfactory results.
Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Łojasiewicz Functions when the Non-Convexity is Averaged-Out
Heavy Ball (HB) nowadays is one of the most popular momentum methods in non-convex optimization.
Small Object Detection via Pixel Level Balancing With Applications to Blood Cell Detection
This method can perform well with blood cell detection in our experiments.
Energy Minimization for Federated Asynchronous Learning on Battery-Powered Mobile Devices via Application Co-running
Energy is an essential, but often forgotten aspect in large-scale federated systems.
Exact Formulas for Finite-Time Estimation Errors of Decentralized Temporal Difference Learning with Linear Function Approximation
In this paper, we consider the policy evaluation problem in multi-agent reinforcement learning (MARL) and derive exact closed-form formulas for the finite-time mean-squared estimation errors of decentralized temporal difference (TD) learning with linear function approximation.
EEG based Emotion Recognition: A Tutorial and Review
Hence, in this paper, we review from the perspective of researchers who try to take the first step on this topic.
Audio Self-supervised Learning: A Survey
Inspired by the humans' cognitive ability to generalise knowledge and skills, Self-Supervised Learning (SSL) targets at discovering general representations from large-scale data without requiring human annotations, which is an expensive and time consuming task.
Convex Programs and Lyapunov Functions for Reinforcement Learning: A Unified Perspective on the Analysis of Value-Based Methods
Value-based methods play a fundamental role in Markov decision processes (MDPs) and reinforcement learning (RL).
Data Augmentation for Depression Detection Using Skeleton-Based Gait Information
Gait analysis provides a non-contact, low-cost, and efficient early screening method for depression.
Revisiting PGD Attacks for Stability Analysis of Large-Scale Nonlinear Systems and Perception-Based Control
We show that the ROA analysis can be approximated as a constrained maximization problem whose goal is to find the worst-case initial condition which shifts the terminal state the most.
Model-Free $μ$ Synthesis via Adversarial Reinforcement Learning
We build a connection between robust adversarial RL and $\mu$ synthesis, and develop a model-free version of the well-known $DK$-iteration for solving state-feedback $\mu$ synthesis with static $D$-scaling.
Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration
Based on the confidential information, a self-adaptive reward function is designed to provide more detailed feedback, and a simulated label generation mechanism is proposed on unsupervised data to reduce over-reliance on labeled data.
Major Depressive Disorder Recognition and Cognitive Analysis Based on Multi-layer Brain Functional Connectivity Networks
On the increase of major depressive disorders (MDD), many researchers paid attention to their recognition and treatment.
Independent Encoder for Deep Hierarchical Unsupervised Image-to-Image Translation
To address this issue, we propose a novel architecture, termed as IEGAN, which removes the encoder of each network and introduces an encoder that is independent of other networks.
SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification
In this paper, we for the first time propose a Self-supervised Multi-scale Skeleton Graph Encoding (SM-SGE) framework that comprehensively models human body, component relations, and skeleton dynamics from unlabeled skeleton graphs of various scales to learn an effective skeleton representation for person Re-ID.
Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification
To fully explore body relations, we construct graphs to model human skeletons from different levels, and for the first time propose a Multi-level Graph encoding approach with Structural-Collaborative Relation learning (MG-SCR) to encode discriminative graph features for person Re-ID.
Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images
Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based solution for weakly-supervised instance segmentation.
Ranked #5 on
Box-supervised Instance Segmentation
on COCO test-dev
(using extra training data)
On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions
When applying imitation learning techniques to fit a policy from expert demonstrations, one can take advantage of prior stability/robustness assumptions on the expert's policy and incorporate such control-theoretic prior knowledge explicitly into the learning process.
Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity
Direct policy search serves as one of the workhorses in modern reinforcement learning (RL), and its applications in continuous control tasks have recently attracted increasing attention.
Lensing magnification: gravitational waves from coalescing stellar-mass binary black holes
The luminosity distance estimation error due to lensing for Einstein Telescope is about $\sigma(\hat{d})/\hat{d} \simeq 10\%$ for the luminosity distance $\gtrsim 25~\mathrm{Gpc}$.
Cosmology and Nongalactic Astrophysics High Energy Astrophysical Phenomena General Relativity and Quantum Cosmology
On the Stability and Convergence of Robust Adversarial Reinforcement Learning: A Case Study on Linear Quadratic Systems
We find: i) the conventional RARL framework (Pinto et al., 2017) can learn a destabilizing policy if the initial policy does not enjoy the robust stability property against the adversary; and ii) with robustly stabilizing initializations, our proposed double-loop RARL algorithm provably converges to the global optimal cost while maintaining robust stability on-the-fly.
Policy Optimization for Markovian Jump Linear Quadratic Control: Gradient-Based Methods and Global Convergence
In this paper, we investigate the global convergence of gradient-based policy optimization methods for quadratic optimal control of discrete-time Markovian jump linear systems (MJLS).
Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition
Existing approaches usually learn action representations by sequential prediction but they suffer from the inability to fully learn semantic information.
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification
This paper proposes a self-supervised gait encoding approach that can leverage unlabeled skeleton data to learn gait representations for person Re-ID.
Self-Supervised Gait Encoding with Locality-Aware Attention for Person Re-Identification
Unlike previous methods, we for the first time propose a generic gait encoding approach that can utilize unlabeled skeleton data to learn gait representations in a self-supervised manner.
Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
In this paper, we for the first time propose a contrastive action learning paradigm named AS-CAL that can leverage different augmentations of unlabeled skeleton data to learn action representations in an unsupervised manner.
EDGE COVID-19: A Web Platform to generate submission-ready genomes for SARS-CoV-2 sequencing efforts
Using an intuitive web-based interface, this workflow automates SARS-CoV-2 reference-based genome assembly, variant calling, lineage determination, and provides the ability to submit the consensus sequence and necessary metadata to GenBank or GISAID.
A Public Website for the Automated Assessment and Validation of SARS-CoV-2 Diagnostic PCR Assays
Summary: Polymerase chain reaction-based assays are the current gold standard for detecting and diagnosing SARS-CoV-2.
Policy Optimization for $\mathcal{H}_{2}$ Linear Control with $\mathcal{H}_{\infty}$ Robustness Guarantee: Implicit Regularization and Global Convergence
In this paper, we study the convergence theory of PO for $\mathcal{H}_{2}$ linear control with $\mathcal{H}_{\infty}$ robustness guarantee.
Policy Learning of MDPs with Mixed Continuous/Discrete Variables: A Case Study on Model-Free Control of Markovian Jump Systems
We implement the (data-driven) natural policy gradient method on different MJLS examples.
A study of resting-state EEG biomarkers for depression recognition
Results: Functional connectivity feature PLI is superior to the linear features and nonlinear features.
A Novel Decision Tree for Depression Recognition in Speech
Depression is a common mental disorder worldwide which causes a range of serious outcomes.
MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis
The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications.
Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems
Recently, policy optimization for control purposes has received renewed attention due to the increasing interest in reinforcement learning.
Policy Optimization for $\mathcal{H}_2$ Linear Control with $\mathcal{H}_\infty$ Robustness Guarantee: Implicit Regularization and Global Convergence
In this paper, we study the convergence theory of PO for $\mathcal{H}_2$ linear control with $\mathcal{H}_\infty$-norm robustness guarantee.
Supervised feature selection with orthogonal regression and feature weighting
Effective features can improve the performance of a model, which can thus help us understand the characteristics and underlying structure of complex data.
Characterizing the Exact Behaviors of Temporal Difference Learning Algorithms Using Markov Jump Linear System Theory
For both the IID and Markov noise cases, we show that the evolution of some augmented versions of the mean and covariance matrix of the TD estimation error exactly follows the trajectory of a deterministic linear time-invariant (LTI) dynamical system.
Identifying Illicit Accounts in Large Scale E-payment Networks -- A Graph Representation Learning Approach
In the context of e-payment transaction graphs, the resultant node and edge embeddings can effectively characterize the user-background as well as the financial transaction patterns of individual account holders.
Local Probabilistic Model for Bayesian Classification: a Generalized Local Classification Model
In this paper, with the insight that the distribution in a local sample space should be simpler than that in the whole sample space, a local probabilistic model established for a local region is expected much simpler and can relax the fundamental assumptions that may not be true in the whole sample space.
Local Distribution in Neighborhood for Classification
Additionally, based on the local distribution, we generate a generalized local classification form that can be effectively applied to various datasets through tuning the parameters.
Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs
Our combination of perspectives leads to a better understanding of accelerated variance-reduced stochastic methods for finite-sum problems.
Analysis of Biased Stochastic Gradient Descent Using Sequential Semidefinite Programs
We present a convergence rate analysis for biased stochastic gradient descent (SGD), where individual gradient updates are corrupted by computation errors.
A Robust Accelerated Optimization Algorithm for Strongly Convex Functions
This work proposes an accelerated first-order algorithm we call the Robust Momentum Method for optimizing smooth strongly convex functions.
Optimization and Control Systems and Control
A Joint Intrinsic-Extrinsic Prior Model for Retinex
We propose a joint intrinsic-extrinsic prior model to estimate both illumination and reflectance from an observed image.
Learning Intrinsic Sparse Structures within Long Short-Term Memory
This work aims to learn structurally-sparse Long Short-Term Memory (LSTM) by reducing the sizes of basic structures within LSTM units, including input updates, gates, hidden states, cell states and outputs.
A Unified Analysis of Stochastic Optimization Methods Using Jump System Theory and Quadratic Constraints
Our proposed model recovers SAGA, SDCA, Finito, and SAG as special cases.
A Learning Based Optimal Human Robot Collaboration with Linear Temporal Logic Constraints
This paper considers an optimal task allocation problem for human robot collaboration in human robot systems with persistent tasks.
An Interval-Based Bayesian Generative Model for Human Complex Activity Recognition
We propose in this paper an atomic action-based Bayesian model that constructs Allen's interval relation networks to characterize complex activities with structural varieties in a probabilistic generative way: By introducing latent variables from the Chinese restaurant process, our approach is able to capture all possible styles of a particular complex activity as a unique set of distributions over atomic actions and relations.
EFTCAMB/EFTCosmoMC: Numerical Notes v3.0
EFTCAMB/EFTCosmoMC are publicly available patches to the CAMB/CosmoMC codes implementing the effective field theory approach to single scalar field dark energy and modified gravity models.
Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology High Energy Physics - Theory Computational Physics
Effective Field Theory of Cosmic Acceleration: constraining dark energy with CMB data
We introduce EFTCAMB/EFTCosmoMC as publicly available patches to the commonly used CAMB/CosmoMC codes.
Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology High Energy Physics - Theory
Effective Field Theory of Cosmic Acceleration: an implementation in CAMB
Second, we extract predictions for linear observables in some parametrized EFT models with a phantom-divide crossing equation of state for dark energy.
Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology High Energy Physics - Theory
