Recently, multi-task feature learning algorithms have received increasing attention and they have been successfully applied to many applications involving high-dimensional data. However, they assume that all tasks share a common set of features, which is too restrictive and may not hold in real-...
Multi-view multi-task learning has recently attracted more and more attention due to its dual-heterogeneity, i.e.,each task has heterogeneous features from multiple views, and probably correlates with other tasks via common views.Existing methods usually suffer from three problems: 1) lack the abi...
aware Network (MPN), which is designed to extract semantically aligned part-level features from pedestrian images. MPN solvesthe body part misalignment problem via multi-task learning (MTL) in the training stage. More specif i cally, it builds one main task (MT)and one auxiliary task (AT) f...
Multi-Task Learning Deep Neural Networks for Speech Feature Denoising Traditional automatic speech recognition (ASR) systems usu- ally get a sharp performance drop when noise presents in speech. To make a robust ASR, we introduce a new model us- ing the multi-task learning deep neural networks ...
novel multi-task multi-view sparse learning problem and exploit the cues from multiple views including various types of visual features, such as intensity, color, and edge, where each feature observation can be sparsely represented by a linear combination of atoms from an adaptive feature dictionary...
The Python classes ARMUL and Baselines in ARMUL.py implement three important cases of ARMUL (vanilla, clustered and low-rank) as well as four baseline procedures (single-task learning, data pooling, clustered MTL and low-rank MTL). The current version supportsmulti-task linear regression: ...
multiguard: provably robust multi-label classification against adversarial examples [Paper] unsupervised model selection for time-series anomaly detection [Paper] perceptual attacks of no-reference image quality models with human-in-the-loop [Paper] robust q -learning algorithm for markov decision...
Wu, Y. Zhuang, Metric learning driven multi-task struc- tured output optimization for robust keypoint tracking, in: Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015.L. Zhao, X. Li, J. Xiao, F. Wu, and Y. Zhuang. Metric learn- ing driven multi-task structured output ...
虽然sklearn中的MultiTaskLasso也是这样的目标函数,并且使用了坐标下降法来求解,但是当目标函数中的损失函数也用L2,1范数时我又懵圈了。 正当我琢磨是不是能把两部分合在一起求解一个L2,1范数时(其实是数... 查看原文 基于L2,1范数的特征选择方法
3.3. Multi-task learning for DOA estimation 3.3.1. Standard multi-task learning image-20220407222910382 Two inputs and two outputs: T-F mask network's input: log-magnitude spectrum DOA network's input: the phase spectrum which is multiplied by the predicted mask Two outputs are the estimated ...