400 citations · 1.6k across the 69 of their papers we have counts for
43 papers · 1 filter
Doubly Stochastic Models: Learning with Unbiased Label Noises and Inference Stability
Haoyi Xiong, Xuhong Li, Boyang Yu +3
Random label noises (or observational noises) widely exist in practical machine learning settings. While previous studies primarily focus on the affects of label noises to the perf…
Facial Affect Analysis: Learning from Synthetic Data & Multi-Task Learning Challenges
Siyang Li, Yifan Xu, Huanyu Wu +4
Facial affect analysis remains a challenging task with its setting transitioned from lab-controlled to in-the-wild situations. In this paper, we present novel frameworks to handle…
PyTSK: A Python Toolbox for TSK Fuzzy Systems
Yuqi Cui, Dongrui Wu, Xue Jiang +1
This paper presents PyTSK, a Python toolbox for developing Takagi-Sugeno-Kang (TSK) fuzzy systems. Based on scikit-learn and PyTorch, PyTSK allows users to optimize TSK fuzzy syste…
AgFlow: Fast Model Selection of Penalized PCA via Implicit Regularization Effects of Gradient Flow
Haiyan Jiang, Haoyi Xiong, Dongrui Wu +2
Principal component analysis (PCA) has been widely used as an effective technique for feature extraction and dimension reduction. In the High Dimension Low Sample Size (HDLSS) sett…
Exploring the Common Principal Subspace of Deep Features in Neural Networks
Haoran Liu, Haoyi Xiong, Yaqing Wang +3
We find that different Deep Neural Networks (DNNs) trained with the same dataset share a common principal subspace in latent spaces, no matter in which architectures (e.g., Convolu…
Optimization Variance: Exploring Generalization Properties of DNNs
Xiao Zhang, Dongrui Wu, Haoyi Xiong +1
Unlike the conventional wisdom in statistical learning theory, the test error of a deep neural network (DNN) often demonstrates double descent: as the model complexity increases, i…
Curse of Dimensionality for TSK Fuzzy Neural Networks: Explanation and Solutions
Yuqi Cui, Dongrui Wu, Yifan Xu
Takagi-Sugeno-Kang (TSK) fuzzy system with Gaussian membership functions (MFs) is one of the most widely used fuzzy systems in machine learning. However, it usually has difficulty…
Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review
Dongrui Wu, Jiaxin Xu, Weili Fang +5
Physiological computing uses human physiological data as system inputs in real time. It includes, or significantly overlaps with, brain-computer interfaces, affective computing, ad…
FCM-RDpA: TSK Fuzzy Regression Model Construction Using Fuzzy C-Means Clustering, Regularization, DropRule, and Powerball AdaBelief
Zhenhua Shi, Dongrui Wu, Chenfeng Guo +3
To effectively optimize Takagi-Sugeno-Kang (TSK) fuzzy systems for regression problems, a mini-batch gradient descent with regularization, DropRule, and AdaBound (MBGD-RDA) algorit…
A Survey on Negative Transfer
Wen Zhang, Lingfei Deng, Lei Zhang +1
Transfer learning (TL) utilizes data or knowledge from one or more source domains to facilitate the learning in a target domain. It is particularly useful when the target domain ha…
Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs
Xiao Zhang, Haoyi Xiong, Dongrui Wu
Over-parameterized deep neural networks (DNNs) with sufficient capacity to memorize random noise can achieve excellent generalization performance, challenging the bias-variance tra…
Pool-Based Unsupervised Active Learning for Regression Using Iterative Representativeness-Diversity Maximization (iRDM)
Ziang Liu, Xue Jiang, Hanbin Luo +3
Active learning (AL) selects the most beneficial unlabeled samples to label, and hence a better machine learning model can be trained from the same number of labeled samples. Most…
Integrating Informativeness, Representativeness and Diversity in Pool-Based Sequential Active Learning for Regression
Ziang Liu, Dongrui Wu
In many real-world machine learning applications, unlabeled samples are easy to obtain, but it is expensive and/or time-consuming to label them. Active learning is a common approac…
MBGD-RDA Training and Rule Pruning for Concise TSK Fuzzy Regression Models
Dongrui Wu
To effectively train Takagi-Sugeno-Kang (TSK) fuzzy systems for regression problems, a Mini-Batch Gradient Descent with Regularization, DropRule, and AdaBound (MBGD-RDA) algorithm…
BoostTree and BoostForest for Ensemble Learning
Changming Zhao, Dongrui Wu, Jian Huang +4
Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and…
Supervised Enhanced Soft Subspace Clustering (SESSC) for TSK Fuzzy Classifiers
Yuqi Cui, Huidong Wang, Dongrui Wu
Fuzzy c-means based clustering algorithms are frequently used for Takagi-Sugeno-Kang (TSK) fuzzy classifier antecedent parameter estimation. One rule is initialized from each clust…
Unsupervised Pool-Based Active Learning for Linear Regression
Ziang Liu, Dongrui Wu
In many real-world machine learning applications, unlabeled data can be easily obtained, but it is very time-consuming and/or expensive to label them. So, it is desirable to be abl…
Supervised Discriminative Sparse PCA with Adaptive Neighbors for Dimensionality Reduction
Zhenhua Shi, Dongrui Wu, Jian Huang +2
Dimensionality reduction is an important operation in information visualization, feature extraction, clustering, regression, and classification, especially for processing noisy hig…
EEG-based Drowsiness Estimation for Driving Safety using Deep Q-Learning
Yurui Ming, Dongrui Wu, Yu-Kai Wang +2
Fatigue is the most vital factor of road fatalities and one manifestation of fatigue during driving is drowsiness. In this paper, we propose using deep Q-learning to analyze an ele…
Empirical Studies on the Properties of Linear Regions in Deep Neural Networks
Xiao Zhang, Dongrui Wu
A deep neural network (DNN) with piecewise linear activations can partition the input space into numerous small linear regions, where different linear functions are fitted. It is b…
Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIs
Zihan Liu, Lubin Meng, Xiao Zhang +2
Multiple convolutional neural network (CNN) classifiers have been proposed for electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, CNN models have been foun…
Discriminative Joint Probability Maximum Mean Discrepancy (DJP-MMD) for Domain Adaptation
Wen Zhang, Dongrui Wu
Maximum mean discrepancy (MMD) has been widely adopted in domain adaptation to measure the discrepancy between the source and target domain distributions. Many existing domain adap…
Active Learning for Black-Box Adversarial Attacks in EEG-Based Brain-Computer Interfaces
Xue Jiang, Xiao Zhang, Dongrui Wu
Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vuln…
Optimize TSK Fuzzy Systems for Classification Problems: Mini-Batch Gradient Descent with Uniform Regularization and Batch Normalization
Yuqi Cui, Jian Huang, Dongrui Wu
Takagi-Sugeno-Kang (TSK) fuzzy systems are flexible and interpretable machine learning models; however, they may not be easily optimized when the data size is large, and/or the dat…