开发旨在增强胎儿监测的创新信息学方法是生殖医学研究的新领域。已经对人工智能(AI)技术进行了几项评论,以改善妊娠结局。他们的限制是专注于特定数据,例如怀孕期间母亲的护理。这项系统的调查旨在探讨人工智能(AI)如何通过超声(US)图像帮助胎儿生长监测。我们使用了八个医学和计算机科学书目数据库,包括PubMed,Embase,Psycinfo,ScienceDirect,IEEE Explore,ACM图书馆,Google Scholar和Web of Science。我们检索了2010年至2021年之间发表的研究。从研究中提取的数据是使用叙述方法合成的。在1269项检索研究中,我们包括了107项与调查中有关该主题的查询的不同研究。我们发现,与3D和4D超声图像(n = 19)相比,2D超声图像更受欢迎(n = 88)。分类是最常用的方法(n = 42),其次是分割(n = 31),与分割(n = 16)集成的分类和其他其他杂项,例如对象检测,回归和增强学习(n = 18)。妊娠结构域中最常见的区域是胎儿头(n = 43),然后是胎儿(n = 31),胎儿心脏(n = 13),胎儿腹部(n = 10),最后是胎儿的面孔(n = 10)。在最近的研究中,深度学习技术主要使用(n = 81),其次是机器学习(n = 16),人工神经网络(n = 7)和增强学习(n = 2)。 AI技术在预测胎儿疾病和鉴定怀孕期间胎儿解剖结构中起着至关重要的作用。需要进行更多的研究来从医生的角度验证这项技术,例如试点研究和有关AI及其在医院环境中的应用的随机对照试验。
translated by 谷歌翻译
The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.
translated by 谷歌翻译
In classic reinforcement learning algorithms, agents make decisions at discrete and fixed time intervals. The physical duration between one decision and the next becomes a critical hyperparameter. When this duration is too short, the agent needs to make many decisions to achieve its goal, aggravating the problem's difficulty. But when this duration is too long, the agent becomes incapable of controlling the system. Physical systems, however, do not need a constant control frequency. For learning agents, it is desirable to operate with low frequency when possible and high frequency when necessary. We propose a framework called Continuous-Time Continuous-Options (CTCO), where the agent chooses options as sub-policies of variable durations. Such options are time-continuous and can interact with the system at any desired frequency providing a smooth change of actions. The empirical analysis shows that our algorithm is competitive w.r.t. other time-abstraction techniques, such as classic option learning and action repetition, and practically overcomes the difficult choice of the decision frequency.
translated by 谷歌翻译
Data scarcity is a notable problem, especially in the medical domain, due to patient data laws. Therefore, efficient Pre-Training techniques could help in combating this problem. In this paper, we demonstrate that a model trained on the time direction of functional neuro-imaging data could help in any downstream task, for example, classifying diseases from healthy controls in fMRI data. We train a Deep Neural Network on Independent components derived from fMRI data using the Independent component analysis (ICA) technique. It learns time direction in the ICA-based data. This pre-trained model is further trained to classify brain disorders in different datasets. Through various experiments, we have shown that learning time direction helps a model learn some causal relation in fMRI data that helps in faster convergence, and consequently, the model generalizes well in downstream classification tasks even with fewer data records.
translated by 谷歌翻译
智能仪表测量值虽然对于准确的需求预测至关重要,但仍面临一些缺点,包括消费者的隐私,数据泄露问题,仅举几例。最近的文献探索了联合学习(FL)作为一种有前途的隐私机器学习替代方案,该替代方案可以协作学习模型,而无需将私人原始数据暴露于短期负载预测中。尽管有着美德,但标准FL仍然容易受到棘手的网络威胁,称为拜占庭式攻击,这是由错误和/或恶意客户进行的。因此,为了提高联邦联邦短期负载预测对拜占庭威胁的鲁棒性,我们开发了一个最先进的基于私人安全的FL框架,以确保单个智能电表的数据的隐私,同时保护FL的安全性模型和架构。我们提出的框架利用了通过符号随机梯度下降(SignsGD)算法的梯度量化的想法,在本地模型培训后,客户仅将梯度的“符号”传输到控制中心。当我们通过涉及一组拜占庭攻击模型的基准神经网络的实验突出显示时,我们提出的方法会非常有效地减轻此类威胁,从而优于常规的FED-SGD模型。
translated by 谷歌翻译
身份验证系统容易受到模型反演攻击的影响,在这种攻击中,对手能够近似目标机器学习模型的倒数。生物识别模型是这种攻击的主要候选者。这是因为反相生物特征模型允许攻击者产生逼真的生物识别输入,以使生物识别认证系统欺骗。进行成功模型反转攻击的主要限制之一是所需的训练数据量。在这项工作中,我们专注于虹膜和面部生物识别系统,并提出了一种新技术,可大大减少必要的训练数据量。通过利用多个模型的输出,我们能够使用1/10进行模型反演攻击,以艾哈迈德和富勒(IJCB 2020)的训练集大小(IJCB 2020)进行虹膜数据,而Mai等人的训练集大小为1/1000。 (模式分析和机器智能2019)的面部数据。我们将新的攻击技术表示为结构性随机,并损失对齐。我们的攻击是黑框,不需要了解目标神经网络的权重,只需要输出向量的维度和值。为了显示对齐损失的多功能性,我们将攻击框架应用于会员推理的任务(Shokri等,IEEE S&P 2017),对生物识别数据。对于IRIS,针对分类网络的会员推断攻击从52%提高到62%的准确性。
translated by 谷歌翻译
自从各种任务的自动化开始以来,自动驾驶车辆一直引起人们的兴趣。人类容易疲惫,在道路上的响应时间缓慢,最重要的是,每年约有135万道路交通事故死亡,这已经是一项危险的任务。预计自动驾驶可以减少世界上驾驶事故的数量,这就是为什么这个问题对研究人员感兴趣的原因。目前,自动驾驶汽车在使车辆自动驾驶时使用不同的算法来实现各种子问题。我们将重点关注增强学习算法,更具体地说是Q学习算法和增强拓扑的神经进化(NEAT),即进化算法和人工神经网络的组合,以训练模型代理,以学习如何在给定路径上驱动。本文将重点介绍上述两种算法之间的比较。
translated by 谷歌翻译
痴呆症是一种神经精神脑障碍,通常会在一个或多个脑细胞停止部分或根本停止工作时发生。在疾病的早期阶段诊断这种疾病是从不良后果中挽救生命并为他们提供更好的医疗保健的至关重要的任务。事实证明,机器学习方法在预测疾病早期痴呆症方面是准确的。痴呆的预测在很大程度上取决于通常从归一化的全脑体积(NWBV)和地图集缩放系数(ASF)收集的收集数据类型,这些数据通常测量并从磁共振成像(MRIS)中进行校正。年龄和性别等其他生物学特征也可以帮助诊断痴呆症。尽管许多研究使用机器学习来预测痴呆症,但我们无法就这些方法的稳定性得出结论,而这些方法在不同的实验条件下更准确。因此,本文研究了有关痴呆预测的机器学习算法的性能的结论稳定性。为此,使用7种机器学习算法和两种功能还原算法,即信息增益(IG)和主成分分析(PCA)进行大量实验。为了检查这些算法的稳定性,IG的特征选择阈值从20%更改为100%,PCA尺寸从2到8。这导致了7x9 + 7x7 = 112实验。在每个实验中,都记录了各种分类评估数据。获得的结果表明,在七种算法中,支持向量机和天真的贝叶斯是最稳定的算法,同时更改选择阈值。同样,发现使用IG似乎比使用PCA预测痴呆症更有效。
translated by 谷歌翻译
尖峰神经网络(SNN)因其高能量效率和分类性能的最新进展而引起了很多关注。但是,与传统的深度学习方法不同,对SNN对对抗性例子的鲁棒性的分析和研究仍然相对欠发达。在这项工作中,我们通过实验和分析三个重要的SNN安全属性来推进对抗机器学习的领域。首先,我们表明对SNN的成功白盒对抗性攻击高度依赖于潜在的替代梯度技术。其次,我们分析了SNN和其他最先进的体系结构(如视觉变压器和大型传输CNN)生成的对抗性示例的可传递性。我们证明,SNN并不经常被视觉变压器和某些类型的CNN产生的对抗典范所欺骗。最后,我们开发了一种新颖的白盒攻击,该攻击生成了能够同时欺骗SNN模型和非SNN模型的对抗性示例。我们的实验和分析是广泛而严格的,涵盖了两个数据集(CIFAR-10和CIFAR-100),五种不同的白色盒子攻击以及十二个不同的分类器模型。
translated by 谷歌翻译
基于图形神经网络(GNN)方法最近已成为处理图数据的流行工具,因为它们能够合并结构信息。GNNS性能的唯一障碍是缺乏标记数据。图像和文本数据的数据增强技术无法用于图形数据,因为图形数据的复杂和非欧几里得结构。这一差距迫使研究人员将注意力转向开发图形数据的数据增强技术。大多数提出的图形数据增强(GDA)技术都是特定于任务的。在本文中,我们根据不同的图形任务调查了现有的GDA技术。这项调查不仅提供了GDA研究界的参考,而且还向其他领域的研究人员提供了必要的信息。
translated by 谷歌翻译