Search Results for author:
Found 67 papers, 24 papers with code
Mixture-of-Experts for Open Set Domain Adaptation: A Dual-Space Detection Approach
Within an MoE, different experts address different input features, producing unique expert routing patterns for different classes in a routing feature space.
Doubly Stochastic Models: Learning with Unbiased Label Noises and Inference Stability
While previous studies primarily focus on the affects of label noises to the performance of learning, our work intends to investigate the implicit regularization effects of the label noises, under mini-batch sampling settings of stochastic gradient descent (SGD), with assumptions that label noises are unbiased.
Adversarial Artifact Detection in EEG-Based Brain-Computer Interfaces
Detection of adversarial examples is crucial to both the understanding of this phenomenon and the defense.
Facial Affect Analysis: Learning from Synthetic Data & Multi-Task Learning Challenges
Facial affect analysis remains a challenging task with its setting transitioned from lab-controlled to in-the-wild situations.
PyTSK: A Python Toolbox for TSK Fuzzy Systems
This paper presents PyTSK, a Python toolbox for developing Takagi-Sugeno-Kang (TSK) fuzzy systems.
AgFlow: Fast Model Selection of Penalized PCA via Implicit Regularization Effects of Gradient Flow
Principal component analysis (PCA) has been widely used as an effective technique for feature extraction and dimension reduction.
Exploring the Common Principal Subspace of Deep Features in Neural Networks
Specifically, we design a new metric $\mathcal{P}$-vector to represent the principal subspace of deep features learned in a DNN, and propose to measure angles between the principal subspaces using $\mathcal{P}$-vectors.
Optimization Variance: Exploring Generalization Properties of DNNs
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, it first follows a classical U-shaped curve and then shows a second descent.
Curse of Dimensionality for TSK Fuzzy Neural Networks: Explanation and Solutions
We show that two defuzzification operations, LogTSK and HTSK, the latter of which is first proposed in this paper, can avoid the saturation.
Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review
Physiological computing uses human physiological data as system inputs in real time.
Implicit Regularization Effects of Unbiased Random Label Noises with SGD
Random label noises (or observational noises) widely exist in practical machinelearning settings.
Empirical Studies on the Convergence of Feature Spaces in Deep Learning
While deep learning is effective to learn features/representations from data, the distributions of samples in feature spaces learned by various architectures for different training tasks (e. g., latent layers of AEs and feature vectors in CNN classifiers) have not been well-studied or compared.
FCM-RDpA: TSK Fuzzy Regression Model Construction Using Fuzzy C-Means Clustering, Regularization, DropRule, and Powerball AdaBelief
To effectively optimize Takagi-Sugeno-Kang (TSK) fuzzy systems for regression problems, a mini-batch gradient descent with regularization, DropRule, and AdaBound (MBGD-RDA) algorithm was recently proposed.
EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks
Test samples with the backdoor key will then be classified into the target class specified by the attacker.
A Survey on Negative Transfer
Transfer learning (TL) utilizes data or knowledge from one or more source domains to facilitate the learning in a target domain.
Transfer Learning for Motor Imagery Based Brain-Computer Interfaces: A Complete Pipeline
Transfer learning (TL) has been widely used in motor imagery (MI) based brain-computer interfaces (BCIs) to reduce the calibration effort for a new subject, and demonstrated promising performance.
Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs
Over-parameterized deep neural networks (DNNs) with sufficient capacity to memorize random noise can achieve excellent generalization performance, challenging the bias-variance trade-off in classical learning theory.
Transfer Learning for EEG-Based Brain-Computer Interfaces: A Review of Progress Made Since 2016
Usually, a calibration session is needed to collect some training data for a new subject, which is time-consuming and user unfriendly.
Integrating Informativeness, Representativeness and Diversity in Pool-Based Sequential Active Learning for Regression
It optimally selects the best few samples to label, so that a better machine learning model can be trained from the same number of labeled samples.
BoostTree and BoostForest for Ensemble Learning
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 more reliable performance.
Pool-Based Unsupervised Active Learning for Regression Using Iterative Representativeness-Diversity Maximization (iRDM)
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.
MBGD-RDA Training and Rule Pruning for Concise TSK Fuzzy Regression Models
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 was recently proposed.
Supervised Enhanced Soft Subspace Clustering (SESSC) for TSK Fuzzy Classifiers
Fuzzy c-means based clustering algorithms are frequently used for Takagi-Sugeno-Kang (TSK) fuzzy classifier antecedent parameter estimation.
Tiny noise, big mistakes: Adversarial perturbations induce errors in Brain-Computer Interface spellers
An electroencephalogram (EEG) based brain-computer interface (BCI) speller allows a user to input text to a computer by thought.
EEG-based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and their Applications
Recent technological advances such as wearable sensing devices, real-time data streaming, machine learning, and deep learning approaches have increased interest in electroencephalographic (EEG) based BCI for translational and healthcare applications.
Unsupervised Pool-Based Active Learning for Linear Regression
So, it is desirable to be able to select the optimal samples to label, so that a good machine learning model can be trained from a minimum amount of labeled data.
Supervised Discriminative Sparse PCA with Adaptive Neighbors for Dimensionality Reduction
Approaches that preserve only the local data structure, such as locality preserving projections, are usually unsupervised (and hence cannot use label information) and uses a fixed similarity graph.
EEG-based Drowsiness Estimation for Driving Safety using Deep Q-Learning
To the best of our knowledge, we are the first to introduce the deep reinforcement learning method to this BCI scenario, and our method can be potentially generalized to other BCI cases.
Empirical Studies on the Properties of Linear Regions in Deep Neural Networks
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.
Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach
Currently, most domain adaptation approaches require the source domains to have the same feature space and label space as the target domain, which limits their applications, as the auxiliary data may have different feature spaces and/or different label spaces.
Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIs
Multiple convolutional neural network (CNN) classifiers have been proposed for electroencephalogram (EEG) based brain-computer interfaces (BCIs).
Discriminative Joint Probability Maximum Mean Discrepancy (DJP-MMD) for Domain Adaptation
Many existing domain adaptation approaches are based on the joint MMD, which is computed as the (weighted) sum of the marginal distribution discrepancy and the conditional distribution discrepancy; however, a more natural metric may be their joint probability distribution discrepancy.
In Vitro Fertilization (IVF) Cumulative Pregnancy Rate Prediction from Basic Patient Characteristics
Tens of millions of women suffer from infertility worldwide each year.
White-Box Target Attack for EEG-Based BCI Regression Problems
Experiments on two BCI regression problems verified that both approaches are effective.
Active Learning for Black-Box Adversarial Attacks in EEG-Based Brain-Computer Interfaces
Learning a good substitute model is critical to the success of these attacks, but it requires a large number of queries to the target model.
Manifold Embedded Knowledge Transfer for Brain-Computer Interfaces
Experiments on four EEG datasets from two different BCI paradigms demonstrated that MEKT outperformed several state-of-the-art transfer learning approaches, and DTE can reduce more than half of the computational cost when the number of source subjects is large, with little sacrifice of classification accuracy.
EEG-Based Driver Drowsiness Estimation Using Feature Weighted Episodic Training
A calibration session is usually required to collect some subject-specific data and tune the model parameters before applying it to a new subject, which is very inconvenient and not user-friendly.
Multi-Task Deep Learning with Dynamic Programming for Embryo Early Development Stage Classification from Time-Lapse Videos
Accurate classification of embryo early development stages can provide embryologists valuable information for assessing the embryo quality, and hence is critical to the success of IVF.
Multi-View Broad Learning System for Primate Oculomotor Decision Decoding
Multi-view learning improves the learning performance by utilizing multi-view data: data collected from multiple sources, or feature sets extracted from the same data source.
Optimize TSK Fuzzy Systems for Classification Problems: Mini-Batch Gradient Descent with Uniform Regularization and Batch Normalization
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 data dimensionality is high.
Recommendations on Designing Practical Interval Type-2 Fuzzy Systems
How to optimize the IT2 fuzzy system?
Canonical Correlation Analysis (CCA) Based Multi-View Learning: An Overview
Canonical correlation analysis (CCA) is very important in MVL, whose main idea is to map data from different views onto a common space with maximum correlation.
Protecting Privacy of Users in Brain-Computer Interface Applications
Machine learning (ML) is revolutionizing research and industry.
Patch Learning
There have been different strategies to improve the performance of a machine learning model, e. g., increasing the depth, width, and/or nonlinearity of the model, and using ensemble learning to aggregate multiple base/weak learners in parallel or in series.
On the Vulnerability of CNN Classifiers in EEG-Based BCIs
Deep learning has been successfully used in numerous applications because of its outstanding performance and the ability to avoid manual feature engineering.
Active Stacking for Heart Rate Estimation
Moreover, active learning can be used to optimally select a few trials from a new subject to label, based on which a stacking ensemble regression model can be trained to aggregate the base estimators.
Optimize TSK Fuzzy Systems for Regression Problems: Mini-Batch Gradient Descent with Regularization, DropRule and AdaBound (MBGD-RDA)
Our final algorithm, mini-batch gradient descent with regularization, DropRule and AdaBound (MBGD-RDA), can achieve fast convergence in training TSK fuzzy systems, and also superior generalization performance in testing.
On the Functional Equivalence of TSK Fuzzy Systems to Neural Networks, Mixture of Experts, CART, and Stacking Ensemble Regression
Fuzzy systems have achieved great success in numerous applications.
Wasserstein Distance based Deep Adversarial Transfer Learning for Intelligent Fault Diagnosis
However, for diverse working conditions in the industry, deep learning suffers two difficulties: one is that the well-defined (source domain) and new (target domain) datasets are with different feature distributions; another one is the fact that insufficient or no labelled data in target domain significantly reduce the accuracy of fault diagnosis.
Multi-Tasking Genetic Algorithm (MTGA) for Fuzzy System Optimization
Experiments on simultaneous optimization of type-1 and interval type-2 fuzzy logic controllers for couple-tank water level control demonstrated that the MTGA can find better fuzzy logic controllers than other approaches.
Active Learning for Regression Using Greedy Sampling
Active learning for regression (ALR) is a methodology to reduce the number of labeled samples, by selecting the most beneficial ones to label, instead of random selection.
Feature Dimensionality Reduction for Video Affect Classification: A Comparative Study
Affective computing has become a very important research area in human-machine interaction.
Transfer Learning Enhanced Common Spatial Pattern Filtering for Brain Computer Interfaces (BCIs): Overview and a New Approach
The electroencephalogram (EEG) is the most widely used input for brain computer interfaces (BCIs), and common spatial pattern (CSP) is frequently used to spatially filter it to increase its signal-to-noise ratio.
Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach
Our approach has three desirable properties: 1) it aligns the EEG trials directly in the Euclidean space, and any signal processing, feature extraction and machine learning algorithms can then be applied to the aligned trials; 2) its computational cost is very low; and, 3) it is unsupervised and does not need any label information from the new subject.
Spatial Filtering for Brain Computer Interfaces: A Comparison between the Common Spatial Pattern and Its Variant
The electroencephalogram (EEG) is the most popular form of input for brain computer interfaces (BCIs).
Affect Estimation in 3D Space Using Multi-Task Active Learning for Regression
Acquisition of labeled training samples for affective computing is usually costly and time-consuming, as affects are intrinsically subjective, subtle and uncertain, and hence multiple human assessors are needed to evaluate each affective sample.
Multi-View Fuzzy Logic System with the Cooperation between Visible and Hidden Views
Multi-view datasets are frequently encountered in learning tasks, such as web data mining and multimedia information analysis.
Offline EEG-Based Driver Drowsiness Estimation Using Enhanced Batch-Mode Active Learning (EBMAL) for Regression
There are many important regression problems in real-world brain-computer interface (BCI) applications, e. g., driver drowsiness estimation from EEG signals.
Agreement Rate Initialized Maximum Likelihood Estimator for Ensemble Classifier Aggregation and Its Application in Brain-Computer Interface
Ensemble learning is a powerful approach to construct a strong learner from multiple base learners.
Active Semi-supervised Transfer Learning (ASTL) for Offline BCI Calibration
Single-trial classification of event-related potentials in electroencephalogram (EEG) signals is a very important paradigm of brain-computer interface (BCI).
Pool-Based Sequential Active Learning for Regression
Given a pool of unlabeled samples, it tries to select the most useful ones to label so that a model built from them can achieve the best possible performance.
OMG - Emotion Challenge Solution
This short paper describes our solution to the 2018 IEEE World Congress on Computational Intelligence One-Minute Gradual-Emotional Behavior Challenge, whose goal was to estimate continuous arousal and valence values from short videos.
EEG-Based User Reaction Time Estimation Using Riemannian Geometry Features
Riemannian geometry has been successfully used in many brain-computer interface (BCI) classification problems and demonstrated superior performance.
Driver Drowsiness Estimation from EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR)
By integrating fuzzy sets with domain adaptation, we propose a novel online weighted adaptation regularization for regression (OwARR) algorithm to reduce the amount of subject-specific calibration data, and also a source domain selection (SDS) approach to save about half of the computational cost of OwARR.
Online and Offline Domain Adaptation for Reducing BCI Calibration Effort
This paper proposes both online and offline weighted adaptation regularization (wAR) algorithms to reduce this calibration effort, i. e., to minimize the amount of labeled subject-specific EEG data required in BCI calibration, and hence to increase the utility of the BCI system.
Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularization
wAR makes use of labeled data from the previous headset and handles class-imbalance, and active learning selects the most informative samples from the new headset to label.
Spatial Filtering for EEG-Based Regression Problems in Brain-Computer Interface (BCI)
Electroencephalogram (EEG) signals are frequently used in brain-computer interfaces (BCIs), but they are easily contaminated by artifacts and noises, so preprocessing must be done before they are fed into a machine learning algorithm for classification or regression.
