步态识别的关键目标是从步态序列中获取框架间的步行习惯代表。但是,与框架内特征相比,框架之间的关系尚未得到足够的关注。在本文中,出于光流的动​​机,提出了双边运动导向的特征,这可以使经典的卷积结构具有直接在功能级别上直接描绘步态运动模式的能力。基于此类特征,我们开发了一组多尺度的时间表示,迫使运动上下文在各个时间分辨率上都可以丰富描述。此外,设计了一个校正块,以消除轮廓的分割噪声,以获取更精确的步态信息。随后,将时间特征集和空间特征组合在一起,以全面地表征步态过程。广泛的实验是在CASIA-B和OU-MVLP数据集上进行的,结果实现了出色的识别性能,这证明了该方法的有效性。
translated by 谷歌翻译
实时音乐伴奏的生成在音乐行业(例如音乐教育和现场表演)中具有广泛的应用。但是,自动实时音乐伴奏的产生仍在研究中,并且经常在逻辑延迟和暴露偏见之间取决于权衡。在本文中,我们提出了Song Driver,这是一种无逻辑延迟或暴露偏见的实时音乐伴奏系统。具体而言,Songdriver将一个伴奏的生成任务分为两个阶段:1)安排阶段,其中变压器模型首先安排了和弦,以实时进行输入旋律,并在下一阶段加速了和弦,而不是播放它们。 2)预测阶段,其中CRF模型基于先前缓存的和弦生成了即将到来的旋律的可播放的多轨伴奏。通过这种两相策略,歌手直接生成即将到来的旋律的伴奏,从而达到了零逻辑延迟。此外,在预测时间步的和弦时,歌手是指第一阶段的缓存和弦,而不是其先前的预测,这避免了暴露偏见问题。由于输入长度通常在实时条件下受到限制,因此另一个潜在的问题是长期顺序信息的丢失。为了弥补这一缺点,我们在当前时间步骤作为全球信息之前从长期音乐作品中提取了四个音乐功能。在实验中,我们在一些开源数据集上训练歌手,以及由中国风格的现代流行音乐得分构建的原始\```````'''aisong数据集。结果表明,歌手在客观和主观指标上均优于现有的SOTA(最先进)模型,同时大大降低了物理潜伏期。
translated by 谷歌翻译
作为对数据有效使用的研究,多源无监督的域适应性将知识从带有标记数据的多个源域转移到了未标记的目标域。但是,目标域中不同域和嘈杂的伪标签之间的分布差异都导致多源无监督域适应方法的性能瓶颈。鉴于此,我们提出了一种将注意力驱动的领域融合和耐噪声学习(ADNT)整合到上述两个问题的方法。首先,我们建立了相反的注意结构,以在特征和诱导域运动之间执行信息。通过这种方法,当域差异降低时,特征的可区分性也可以显着提高。其次,基于无监督的域适应训练的特征,我们设计了自适应的反向横向熵损失,该损失可以直接对伪标签的产生施加约束。最后,结合了这两种方法,几个基准的实验结果进一步验证了我们提出的ADNT的有效性,并证明了优于最新方法的性能。
translated by 谷歌翻译
单通道水下声学信号的分离是一个具有挑战性的问题,具有实际意义。鉴于信号分离问题的信号数量未知数量,我们提出了一个具有固定数量输出通道的解决方案,从而避免了由输出与目标对齐所引起的排列问题引起的维数灾难。具体而言,我们修改了针对基于自动编码器的已知信号开发的两种算法,这些算法是可以解释的。我们还提出了一种新的绩效评估方法,用于使用静音通道的情况。在辐射船舶噪声的模拟混合物上进行的实验表明,所提出的解决方案可以实现与已知数量信号获得的相似的分离性能。静音通道输出也很好。
translated by 谷歌翻译
Non-convex AC optimal power flow (AC-OPF) is a fundamental optimization problem in power system analysis. The computational complexity of conventional solvers is typically high and not suitable for large-scale networks in real-time operation. Hence, deep learning based approaches have gained intensive attention to conduct the time-consuming training process offline. Supervised learning methods may yield a feasible AC-OPF solution with a small optimality gap. However, they often need conventional solvers to generate the training dataset. This paper proposes an end-to-end unsupervised learning based framework for AC-OPF. We develop a deep neural network to output a partial set of decision variables while the remaining variables are recovered by solving AC power flow equations. The fast decoupled power flow solver is adopted to further reduce the computational time. In addition, we propose using a modified augmented Lagrangian function as the training loss. The multipliers are adjusted dynamically based on the degree of constraint violation. Extensive numerical test results corroborate the advantages of our proposed approach over some existing methods.
translated by 谷歌翻译
This work studies the multi-task functional linear regression models where both the covariates and the unknown regression coefficients (called slope functions) are curves. For slope function estimation, we employ penalized splines to balance bias, variance, and computational complexity. The power of multi-task learning is brought in by imposing additional structures over the slope functions. We propose a general model with double regularization over the spline coefficient matrix: i) a matrix manifold constraint, and ii) a composite penalty as a summation of quadratic terms. Many multi-task learning approaches can be treated as special cases of this proposed model, such as a reduced-rank model and a graph Laplacian regularized model. We show the composite penalty induces a specific norm, which helps to quantify the manifold curvature and determine the corresponding proper subset in the manifold tangent space. The complexity of tangent space subset is then bridged to the complexity of geodesic neighbor via generic chaining. A unified convergence upper bound is obtained and specifically applied to the reduced-rank model and the graph Laplacian regularized model. The phase transition behaviors for the estimators are examined as we vary the configurations of model parameters.
translated by 谷歌翻译
机器人系统的参数调整是一项耗时且具有挑战性的任务,通常依赖于人类操作员的领域专业知识。此外,由于许多原因,现有的学习方法不适合参数调整,包括:缺乏“良好机器人行为”的明确数值指标;由于依赖现实世界实验数据而导致的数据有限;以及参数组合的较大搜索空间。在这项工作中,我们提出了一种开源MATLAB偏好优化和用于系统探索高维参数空间的机器人工具箱(Polar)的学习算法,该算法使用基于人类的基于人类偏好的学习。该工具箱的这个目的是系统,有效地实现两个目标之一:1)优化人类操作员偏好的机器人行为; 2)学习操作员的基本偏好格局,以更好地了解可调参数和操作员偏好之间的关系。极性工具箱仅使用主观反馈机制(成对的偏好,共同反馈和序数标签)来实现这些目标,以推断出贝叶斯后验,而不是基本的奖励功能决定用户的偏好。我们证明了工具箱在模拟中的性能,并介绍了基于人类偏好的学习的各种应用。
translated by 谷歌翻译
资源受限的分类任务在实际应用中很常见,例如为疾病诊断分配测试,填补有限数量的职位时雇用决策以及在有限检查预算下制造环境中的缺陷检测。典型的分类算法将学习过程和资源约束视为两个单独的顺序任务。在这里,我们设计了一种自适应学习方法,该方法通过迭代微调错误分类成本来考虑资源限制和共同学习。通过使用公开可用数据集的结构化实验研究,我们评估了采用建议方法的决策树分类器。自适应学习方法的表现要比替代方法要好得多,尤其是对于困难的分类问题,在这种问题上,普通方法的表现可能不令人满意。我们将适应性学习方法设想为处理资源受限分类问题的技术曲目的重要补充。
translated by 谷歌翻译
Multi-view unsupervised feature selection has been proven to be efficient in reducing the dimensionality of multi-view unlabeled data with high dimensions. The previous methods assume all of the views are complete. However, in real applications, the multi-view data are often incomplete, i.e., some views of instances are missing, which will result in the failure of these methods. Besides, while the data arrive in form of streams, these existing methods will suffer the issues of high storage cost and expensive computation time. To address these issues, we propose an Incremental Incomplete Multi-view Unsupervised Feature Selection method (I$^2$MUFS) on incomplete multi-view streaming data. By jointly considering the consistent and complementary information across different views, I$^2$MUFS embeds the unsupervised feature selection into an extended weighted non-negative matrix factorization model, which can learn a consensus clustering indicator matrix and fuse different latent feature matrices with adaptive view weights. Furthermore, we introduce the incremental leaning mechanisms to develop an alternative iterative algorithm, where the feature selection matrix is incrementally updated, rather than recomputing on the entire updated data from scratch. A series of experiments are conducted to verify the effectiveness of the proposed method by comparing with several state-of-the-art methods. The experimental results demonstrate the effectiveness and efficiency of the proposed method in terms of the clustering metrics and the computational cost.
translated by 谷歌翻译
在这项工作中,我们提出了一种深度自适应采样(DAS)方法,用于求解部分微分方程(PDE),其中利用深神经网络近似PDE和深生成模型的解决方案,用于生成改进训练集的新的搭配点。 DAS的整体过程由两个组件组成:通过最小化训练集中的搭配点上的剩余损失来解决PDE,并生成新的训练集,以进一步提高电流近似解的准确性。特别地,我们将残差作为概率密度函数进行处理,并用一个被称为Krnet的深生成模型近似它。来自Krnet的新样品与残留物诱导的分布一致,即,更多样品位于大残留的区域中,并且较少的样品位于小残余区域中。类似于经典的自适应方法,例如自适应有限元,Krnet作为引导训练集的改进的错误指示器。与用均匀分布的搭配点获得的神经网络近似相比,发达的算法可以显着提高精度,特别是对于低规律性和高维问题。我们展示了一个理论分析,表明所提出的DAS方法可以减少误差并展示其与数值实验的有效性。
translated by 谷歌翻译