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
Of late, insurance fraud detection has assumed immense significance owing to the huge financial & reputational losses fraud entails and the phenomenal success of the fraud detection techniques. Insurance is majorly divided into two categories: (i) Life and (ii) Non-life. Non-life insurance in turn includes health insurance and auto insurance among other things. In either of the categories, the fraud detection techniques should be designed in such a way that they capture as many fraudulent transactions as possible. Owing to the rarity of fraudulent transactions, in this paper, we propose a chaotic variational autoencoder (C-VAE to perform one-class classification (OCC) on genuine transactions. Here, we employed the logistic chaotic map to generate random noise in the latent space. The effectiveness of C-VAE is demonstrated on the health insurance fraud and auto insurance datasets. We considered vanilla Variational Auto Encoder (VAE) as the baseline. It is observed that C-VAE outperformed VAE in both datasets. C-VAE achieved a classification rate of 77.9% and 87.25% in health and automobile insurance datasets respectively. Further, the t-test conducted at 1% level of significance and 18 degrees of freedom infers that C-VAE is statistically significant than the VAE.
translated by 谷歌翻译
Running machine learning inference on tiny devices, known as TinyML, is an emerging research area. This task requires generating inference code that uses memory frugally, a task that standard ML frameworks are ill-suited for. A deployment framework for TinyML must be a) parametric in the number representation to take advantage of the emerging representations like posits, b) carefully assign high-precision to a few tensors so that most tensors can be kept in low-precision while still maintaining model accuracy, and c) avoid memory fragmentation. We describe MinUn, the first TinyML framework that holistically addresses these issues to generate efficient code for ARM microcontrollers (e.g., Arduino Uno, Due and STM32H747) that outperforms the prior TinyML frameworks.
translated by 谷歌翻译
图神经网络(GNN)正在在各种应用领域中实现出色的性能。但是,GNN容易受到输入数据中的噪声和对抗性攻击。在噪音和对抗性攻击方面使GNN坚固是一个重要的问题。现有的GNN防御方法在计算上是要求的,并且不可扩展。在本文中,我们提出了一个通用框架,用于鲁棒化的GNN称为加权laplacian GNN(RWL-GNN)。该方法将加权图拉普拉斯学习与GNN实现结合在一起。所提出的方法受益于Laplacian矩阵的积极半定义特性,具有光滑度和潜在特征,通过制定统一的优化框架,从而确保丢弃对抗性/嘈杂的边缘,并适当加权图中的相关连接。为了进行演示,实验是通过图形卷积神经网络(GCNN)体系结构进行的,但是,所提出的框架很容易适合任何现有的GNN体系结构。使用基准数据集的仿真结果建立了所提出方法的疗效,无论是准确性还是计算效率。可以在https://github.com/bharat-runwal/rwl-gnn上访问代码。
translated by 谷歌翻译
现实世界的行为通常是由多种代理之间复杂的相互作用来塑造的。为了可靠地研究多代理行为,无监督和自我监督的学习的进步使从轨迹数据中学到了各种不同的行为表示。迄今为止,还没有一组统一的基准测试,可以在广泛的行为分析设置中进行定量和系统地比较方法。我们的目的是通过引入来自现实世界行为神经科学实验的大规模,多代理轨迹数据集来解决这一问题,该数据集涵盖了一系列行为分析任务。我们的数据集由来自通用模型生物的轨迹数据组成,其中有960万帧的小鼠数据和440万帧的飞行数据,在各种实验环境中,例如不同的菌株,相互作用的长度和光遗传学刺激。框架的子集还包括专家注销的行为标签。我们数据集的改进对应于跨多种生物的行为表示,并能够捕获常见行为分析任务的差异。
translated by 谷歌翻译
在本文中,我们使用语言数据收集的现场方法讨论了四种低资源印度语语言的演讲语料库的过程中的工作 - Awadhi,Bhojpuri,Braj和Magahi。目前,语料库的总大小约为18小时(每种语言约4-5小时),并用语法信息进行转录和注释,例如词性标签,形态学特征和普遍的依赖关系。我们讨论了以这些语言收集数据的方法,其中大多数是在Covid-19大流行中心进行的,其中之一是为低收入群体带来一些额外的收入,说这些语言。在本文中,我们还讨论了这些语言中自动语音识别系统的基线实验的结果。
translated by 谷歌翻译
生物标志物确定患者对治疗的反应。随着基于变压器网络的人工智能的最新进展,仅进行了有限的研究来衡量具有挑战性的组织病理学图像的性能。在本文中,我们研究了众多最先进的变压器网络对免疫组织蛋白质细胞分割免疫组织癌(IHC)幻灯片中结肠癌的众多最先进的变压器网络的疗效。广泛而全面的实验结果证实,与其余评估的变压器和有效的U-NET方法相比,Missformer的骰子得分最高74.85%。
translated by 谷歌翻译
语言模型既展示了定量的改进,又展示了新的定性功能,随着规模的增加。尽管它们具有潜在的变革性影响,但这些新能力的特征却很差。为了为未来的研究提供信息,为破坏性的新模型能力做准备,并改善社会有害的效果,至关重要的是,我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战,我们介绍了超越模仿游戏基准(Big Bench)。 Big Bench目前由204个任务组成,由132家机构的442位作者贡献。任务主题是多样的,从语言学,儿童发展,数学,常识性推理,生物学,物理学,社会偏见,软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号,Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为,跨越了数百万到数十亿个参数。此外,一个人类专家评估者团队执行了所有任务,以提供强大的基准。研究结果包括:模型性能和校准都随规模改善,但绝对的术语(以及与评估者的性能相比);在模型类中的性能非常相似,尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分,而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标;社交偏见通常会随着含糊不清的环境而随着规模而增加,但这可以通过提示来改善。
translated by 谷歌翻译
本文提出了一种模型预测控制(MPC)静态跟踪静态和动态障碍物的算法。我们的主要贡献在于提高了潜在的非凸轨道优化的计算途径和可靠性。结果是MPC算法,在笔记本电脑和嵌入式硬件设备(如Jetson TX2)上运行实时运行。我们的方法依赖于在由此产生的轨迹优化中引起多凸结构的跟踪,碰撞和遮挡约束的新颖重新装配。我们利用拆分Bregman迭代技术利用这些数学结构,最终将我们的MPC减少到几毫秒内可解决的一系列凸二次程序。即使考虑到目标轨迹和动态障碍物的简单恒定速度预测,我们的快速重新计划允许在复杂环境中遮挡和无碰撞跟踪。我们在现实物理发动机中进行广泛的台面标记,并表明我们的MPC在可视性,平滑度和计算时度量中表现出最先进的算法。
translated by 谷歌翻译
在视觉检索系统中,更新嵌入式模型需要每条数据的重新计算功能。该昂贵的过程称为回填。最近,提出了向后兼容培训(BCT)的想法。为避免回填的成本,BCT修改了对新模型的培训,使其与旧模型兼容的表示。但是,BCT可以显着地阻碍新模型的性能。在这项工作中,我们提出了一种新的学习范例来代表学习:前进兼容培训(FCT)。在FCT中,当旧型号接受培训时,我们还为未来的未知版本做好准备。我们提出学习侧信息,每个样本的辅助功能,促进了模型的未来更新。为了开发一个强大而灵活的模型兼容框架,我们将侧面信息与旧嵌入到新嵌入的前向转换相结合。新模型的培训没有修改,因此,其准确性不会降低。与各种数据集的BCT相比,我们展示了显着的检索准确性改进:Imagenet-1K(+ 18.1%),Place-365(+ 5.4%)和VGG-Face2(+ 8.3%)。 FCT在不同数据集,损失和架构培训时获得模型兼容性。
translated by 谷歌翻译