The proceedings contain 98 papers. The topics discussed include: hierarchical graph neural nets can capture long-range interactions;self-attention for audio super-resolution;deep complex convolutional recurrent networ...
ISBN:
(纸本)9781728163383
The proceedings contain 98 papers. The topics discussed include: hierarchical graph neural nets can capture long-range interactions;self-attention for audio super-resolution;deep complex convolutional recurrent network for multi-channel speech enhancement and dereverberation;model selection of kernel ridge regression for extrapolation;optimizing time domain fully convolutional networks for 3D speech enhancement in a reverberant environment using perceptual losses;online DOA estimation for noninteger linear antenna arrays in coarray domain;tracking of quantized signals based on online kernel regression;and robustness-aware filter pruning for robust neural networks against adversarial attacks.
The proceedings contain 98 papers. The topics discussed include: optimal pricing in black box producer-consumer Stackelberg games using revealed preference feedback;learning warm-start points for AC optimal power flow...
ISBN:
(纸本)9781728108247
The proceedings contain 98 papers. The topics discussed include: optimal pricing in black box producer-consumer Stackelberg games using revealed preference feedback;learning warm-start points for AC optimal power flow;minimax active learning via minimal model capacity;multi-step chord sequence prediction based on aggregated multi-scale encoder-decoder networks;robust hybrid beamforming with quantized deep neural networks;a machinelearning approach for classifying faults in microgrids using wavelet decomposition;robust importance-weighted cross-validation under sample selection bias;interpretable online banking fraud detection based on hierarchical attention mechanism;and a benchmark study of backdoor data poisoning defenses for deep neural network classifiers and a novel defense.
The proceedings contain 75 papers. The topics discussed include: building efficient radial basis function kernel classifiers using iterative methods;the correntropy MACE filter for image recognition;sparse feature ext...
详细信息
ISBN:
(纸本)1424406560
The proceedings contain 75 papers. The topics discussed include: building efficient radial basis function kernel classifiers using iterative methods;the correntropy MACE filter for image recognition;sparse feature extraction using generalised partial least squares;automatic image classification by a granular computing approach;a joint probabilistic-deterministic approach using source-filter modeling of speech signal for single channel speech separation;wavelet based nonlinear separation of images;flexible ICA in complex and nonlinear environment by mutual information minimization;separating nonlinear image mixtures using a physical model trained with ICA;blind separation of positive dependent sources by non-negative least-correlated component analysis;adaptable nonlinearity for complex maximization of nongaussianity and a fixed-point algorithm;gradient and fixed-point complex ICA algorithms based on kurtosis maximization;and map model selection for context trees.
The proceedings contain 89 papers. The topics discussed include: mahalanobis-based one-class classification;improving the robustness of surface enhanced Raman spectroscopy based sensors by Bayesian non-negative matrix...
ISBN:
(纸本)9781479936946
The proceedings contain 89 papers. The topics discussed include: mahalanobis-based one-class classification;improving the robustness of surface enhanced Raman spectroscopy based sensors by Bayesian non-negative matrix factorization;data mining by nonnegative tensor approximation;non-negative tensor factorization with missing data for the modeling of gene expressions in the human brain;multiple speaker tracking with the factorial von mises-fisher filter;a probabilistic approach to hearing loss compensation;coherent time modeling of semi-Markov models with application to real-time audio-to-score alignment;ultra-low-power voice-activity-detector through context and resource-cost-aware feature selection in decision trees;and a probabilistic approach for phase estimation in single-channel speech enhancement using von mises phase priors.
The proceedings contain 121 papers. The topics discussed include: composer style-specific symbolic music generation using vector quantized discrete diffusion models;sparsification of deep neural networks via ternary q...
ISBN:
(纸本)9798350372250
The proceedings contain 121 papers. The topics discussed include: composer style-specific symbolic music generation using vector quantized discrete diffusion models;sparsification of deep neural networks via ternary quantization;orthogonal symmetric nonnegative matrix tri-factorization;convexity based pruning of speech representation models;discriminative community detection for multiplex networks;novel gradient sparsification algorithm via Bayesian inference;adaptive semantic image transmission using generative foundation model;FOLEYGEN: visually-guided audio generation;graph-vector autorregressive model for lithium-ion cell capacity estimation;and episodic fine-tuning prototypical networks for optimization-based few-shot learning: application to audio classification.
The proceedings contain 62 papers. The topics discussed include: general robust subband adaptive filtering for echo cancellation;regression with an ensemble of noisy base functions;mmcc-music: a robust direction of ar...
ISBN:
(纸本)9781665485470
The proceedings contain 62 papers. The topics discussed include: general robust subband adaptive filtering for echo cancellation;regression with an ensemble of noisy base functions;mmcc-music: a robust direction of arrival estimator based on maximum mixture correntropy criterion under alpha-stable distributed noise;joint covariate-alignment and concept-alignment: a framework for domain generalization;machinelearning-based heart disease prediction: a study for home personalized care;an efficient transformer-based model for voice activity detection;multi-patches cooperative point cloud denoising algorithm based on locally linear embedding;neural knowledge transfer for sentiment analysis in texts with figurative language;orthogonal maximum correntropy learning;an alternative approach for distributed parameter estimation under gaussian settings;and an integration development of traditional algorithm and neural network for active noise cancellation.
The proceedings contain 82 papers. The topics discussed include: mutual information based dimensionality reduction with application to non-linear regression;functional data representation using correntropy locally lin...
ISBN:
(纸本)9781424478774
The proceedings contain 82 papers. The topics discussed include: mutual information based dimensionality reduction with application to non-linear regression;functional data representation using correntropy locally linear embedding;local dimensionality reduction for multiple instance learning;multiplicative updates for t-SNE;manifold-respecting probabilistic matrix tri-factorization;single-frame image super-resolution unising a pearson type VII MRF;a one-pass resource-allocating codebook for patch-based visual object recognition;learning spatial filters for multispectral image segmentation;improperness measures for quaternion random vectors;Bayesian BCJR for channel equalization and decoding;reinforcement learning method for energy efficient cooperative multiband spectrum sensing;and error-related potential recorded by EEG in the context of a P300 mind speller brain-computer interface.
The proceedings contain 125 papers. The topics discussed include: on NUP priors and gaussian message passing;greedy online change point detection;stream-based active learning with adaptive uncertainty and diversity th...
ISBN:
(纸本)9798350324112
The proceedings contain 125 papers. The topics discussed include: on NUP priors and gaussian message passing;greedy online change point detection;stream-based active learning with adaptive uncertainty and diversity thresholds;an ensemble link prediction framework with AUC-guided leaderboard probing for volunteer collaboration prediction challenge;exploiting music source separation for singing voice detection;semantic-aware image compressed sensing;graph-based multi-task learning for fault detection in smart grid;predicting room impulse responses through encoder-decoder convolutional neural networks;dual quaternion rotational and translational equivariance in 3D rigid motion modelling;and post-hoc explainability of bi-rads descriptors in a multi-task framework for breast cancer detection and segmentation.
The proceedings contain 96 papers. The topics discussed include: protein subcellular localization prediction based on profile alignment and gene ontology;a sinusoidal audio and speech analysis/synthesis model based on...
ISBN:
(纸本)9781457716232
The proceedings contain 96 papers. The topics discussed include: protein subcellular localization prediction based on profile alignment and gene ontology;a sinusoidal audio and speech analysis/synthesis model based on improved EMD by adding pure tone;data representation and feature selection for colorimetric sensor arrays used as explosives detectors;efficient preference learning with pairwise continuous observations and Gaussian processes;active one-class learning by kernel density estimation;large scale topic modeling made practical;underdetermined convolutive blind source separation using a novel mixing matrix estimation and MMSE-based source estimation;robust online estimation of the vanishing point for vehicle mounted cameras;Gaussian process for human motion modeling: a comparative study;multi-resolution inversion algorithm for the attenuated radon transform;and a reproducing kernel Hilbert space formulation of the principle of relevant information.
The proceedings contain 75 papers. The topics discussed include: model-order selection in statistical shape models;monaural speech separation using a phase-aware deep denoising auto encoder;variational Bayesian partia...
ISBN:
(纸本)9781538654774
The proceedings contain 75 papers. The topics discussed include: model-order selection in statistical shape models;monaural speech separation using a phase-aware deep denoising auto encoder;variational Bayesian partially observed non-negative tensor factorization;nonlinear probabilistic latent variable models for groupwise correspondence analysis in brain structures;uncertainty bounds for kernel-based regression: a Bayesian SPS approach;frame-level proximity and touch recognition using capacitive sensing and semi-supervised sequential modeling;a variance modeling framework based on variational autoencoders for speech enhancement;correcting boundary over-exploration deficiencies in Bayesian optimization with virtual derivative sign observations;single-channel EEG classification by multi-channel tensor subspace learning and regression;learning sparse structured ensembles with stochastic gradient MCMC sampling and network pruning;convolutional neural networks for noise signal recognition;deep learning based speed estimation for constraining strapdown inertial navigation on smartphones;a multi-layer perceptron applied to number of target indication for direction-of-arrival estimation in automotive radar sensors;APE: archetypal-prototypal embeddings for audio classification;a characterization of the edge of criticality in binary echo state networks;and controlling blood glucose levels in patients with type 1 diabetes using fitted q-iterations and functional features.
暂无评论