We test the performance of GAN models for lip-synchronization. For this, we reimplement LipGAN in Pytorch, train it on the dataset GRID and compare it to our own variation, L1WGAN-GP, adapted to the LipGAN architecture and also trained on GRID.
translated by 谷歌翻译
Data-driven models such as neural networks are being applied more and more to safety-critical applications, such as the modeling and control of cyber-physical systems. Despite the flexibility of the approach, there are still concerns about the safety of these models in this context, as well as the need for large amounts of potentially expensive data. In particular, when long-term predictions are needed or frequent measurements are not available, the open-loop stability of the model becomes important. However, it is difficult to make such guarantees for complex black-box models such as neural networks, and prior work has shown that model stability is indeed an issue. In this work, we consider an aluminum extraction process where measurements of the internal state of the reactor are time-consuming and expensive. We model the process using neural networks and investigate the role of including skip connections in the network architecture as well as using l1 regularization to induce sparse connection weights. We demonstrate that these measures can greatly improve both the accuracy and the stability of the models for datasets of varying sizes.
translated by 谷歌翻译
High content imaging assays can capture rich phenotypic response data for large sets of compound treatments, aiding in the characterization and discovery of novel drugs. However, extracting representative features from high content images that can capture subtle nuances in phenotypes remains challenging. The lack of high-quality labels makes it difficult to achieve satisfactory results with supervised deep learning. Self-Supervised learning methods, which learn from automatically generated labels has shown great success on natural images, offer an attractive alternative also to microscopy images. However, we find that self-supervised learning techniques underperform on high content imaging assays. One challenge is the undesirable domain shifts present in the data known as batch effects, which may be caused by biological noise or uncontrolled experimental conditions. To this end, we introduce Cross-Domain Consistency Learning (CDCL), a novel approach that is able to learn in the presence of batch effects. CDCL enforces the learning of biological similarities while disregarding undesirable batch-specific signals, which leads to more useful and versatile representations. These features are organised according to their morphological changes and are more useful for downstream tasks - such as distinguishing treatments and mode of action.
translated by 谷歌翻译
Objective: Imbalances of the electrolyte concentration levels in the body can lead to catastrophic consequences, but accurate and accessible measurements could improve patient outcomes. While blood tests provide accurate measurements, they are invasive and the laboratory analysis can be slow or inaccessible. In contrast, an electrocardiogram (ECG) is a widely adopted tool which is quick and simple to acquire. However, the problem of estimating continuous electrolyte concentrations directly from ECGs is not well-studied. We therefore investigate if regression methods can be used for accurate ECG-based prediction of electrolyte concentrations. Methods: We explore the use of deep neural networks (DNNs) for this task. We analyze the regression performance across four electrolytes, utilizing a novel dataset containing over 290000 ECGs. For improved understanding, we also study the full spectrum from continuous predictions to binary classification of extreme concentration levels. To enhance clinical usefulness, we finally extend to a probabilistic regression approach and evaluate different uncertainty estimates. Results: We find that the performance varies significantly between different electrolytes, which is clinically justified in the interplay of electrolytes and their manifestation in the ECG. We also compare the regression accuracy with that of traditional machine learning models, demonstrating superior performance of DNNs. Conclusion: Discretization can lead to good classification performance, but does not help solve the original problem of predicting continuous concentration levels. While probabilistic regression demonstrates potential practical usefulness, the uncertainty estimates are not particularly well-calibrated. Significance: Our study is a first step towards accurate and reliable ECG-based prediction of electrolyte concentration levels.
translated by 谷歌翻译
As spatial audio is enjoying a surge in popularity, data-driven machine learning techniques that have been proven successful in other domains are increasingly used to process head-related transfer function measurements. However, these techniques require much data, whereas the existing datasets are ranging from tens to the low hundreds of datapoints. It therefore becomes attractive to combine multiple of these datasets, although they are measured under different conditions. In this paper, we first establish the common ground between a number of datasets, then we investigate potential pitfalls of mixing datasets. We perform a simple experiment to test the relevance of the remaining differences between datasets when applying machine learning techniques. Finally, we pinpoint the most relevant differences.
translated by 谷歌翻译
This paper presents an evaluation of the quality of automatically generated reading comprehension questions from Swedish text, using the Quinductor method. This method is a light-weight, data-driven but non-neural method for automatic question generation (QG). The evaluation shows that Quinductor is a viable QG method that can provide a strong baseline for neural-network-based QG methods.
translated by 谷歌翻译
Using 3D CNNs on high resolution medical volumes is very computationally demanding, especially for large datasets like the UK Biobank which aims to scan 100,000 subjects. Here we demonstrate that using 2D CNNs on a few 2D projections (representing mean and standard deviation across axial, sagittal and coronal slices) of the 3D volumes leads to reasonable test accuracy when predicting the age from brain volumes. Using our approach, one training epoch with 20,324 subjects takes 40 - 70 seconds using a single GPU, which is almost 100 times faster compared to a small 3D CNN. These results are important for researchers who do not have access to expensive GPU hardware for 3D CNNs.
translated by 谷歌翻译
未知的非线性动力学通常会限制前馈控制的跟踪性能。本文的目的是开发一个可以使用通用函数近似器来补偿这些未知非线性动力学的前馈控制框架。前馈控制器被参数化为基于物理模型和神经网络的平行组合,在该组合中,两者都共享相同的线性自回旋(AR)动力学。该参数化允许通过Sanathanan-Koerner(SK)迭代进行有效的输出误差优化。在每个Sk-itteration中,神经网络的输出在基于物理模型的子空间中通过基于正交投影的正则化受到惩罚,从而使神经网络仅捕获未建模的动力学,从而产生可解释的模型。
translated by 谷歌翻译
正在为军事和商业用途开发越野自动驾驶的无人接地车辆(UGV),以在偏远地区提供关键的供应,帮助绘制和监视,并在有争议的环境中协助战争战士。由于越野环境的复杂性以及地形,照明条件,昼夜和季节性变化的变化,用于感知环境的模型必须处理大量的输入可变性。当前的数据集用于训练越野自动导航的感知模型在季节,位置,语义类别以及一天中的时间中缺乏多样性。我们测试了以下假设:由于输入分布漂移,在单个数据集上训练的模型可能无法推广到其他越野导航数据集和新位置。此外,我们研究了如何组合多个数据集来训练基于语义分割的环境感知模型,并表明训练模型以捕获不确定性可以通过显着的余量提高模型性能。我们将蒙版的方法扩展到语义分割任务中的不确定性量化方法,并将其与蒙特卡洛辍学和标准基线进行比较。最后,我们测试了在新测试环境中从UGV平台收集的数据的方法。我们表明,具有不确定性量化的开发的感知模型可以在UGV上可用,以支持在线感知和导航任务。
translated by 谷歌翻译
在科学计算的许多领域越来越流行的人工神经网络(ANN)的大量使用迅速增加了现代高性能计算系统的能源消耗。新型的神经形态范式提供了一种吸引人的替代方案,它直接在硬件中实施了ANN。但是,对于科学计算中用例使用ANN在神经形态硬件上运行ANN的实际好处知之甚少。在这里,我们提出了一种方法,用于测量使用常规硬件的ANN来计算推理任务的时间。此外,我们为这些任务设计了一个体系结构,并根据最先进的模拟内存计算(AIMC)平台估算了相同的指标,这是神经形态计算中的关键范例之一。在二维凝结物质系统中的量子多体物理学中的用例比较两种方法,并在粒子物理学中大型强子对撞机上以40 MHz的速率以40 MHz的速率进行异常检测。我们发现,与传统硬件相比,AIMC最多可以达到一个较短的计算时间,最高三个数量级的能源成本。这表明使用神经形态硬件进行更快,更可持续的科学计算的潜力。
translated by 谷歌翻译