我们研究了机器学习(ML)分类技术的误差概率收敛到零的速率的性能。利用大偏差理论,我们为ML分类器提供了数学条件,以表现出误差概率,这些误差概率呈指数级消失,例如$ \ sim \ exp \ left(-n \,i + o(i + o(n)\ right)$,其中$ n $是可用于测试的信息的数量(或其他相关参数,例如图像中目标的大小),而$ i $是错误率。这样的条件取决于数据驱动的决策功能的累积生成功能的Fenchel-Legendre变换(D3F,即,在做出最终二进制决策之前的阈值)在训练阶段中学到的。因此,D3F以及相关的错误率$ $ $取决于给定的训练集,该集合假定有限。有趣的是,可以根据基础统计模型的可用信息生成的可用数据集或合成数据集对这些条件进行验证和测试。换句话说,分类误差概率收敛到零,其速率可以在可用于培训的数据集的一部分上计算。与大偏差理论一致,我们还可以以足够大的$ n $为高斯分布的归一化D3F统计量来确定收敛性。利用此属性设置所需的渐近错误警报概率,从经验上来说,即使对于$ n $的非常现实的值,该属性也是准确的。此外,提供了近似错误概率曲线$ \ sim \ sim \ sim \ sim \ exp \ left(-n \,i \ right)$,这要归功于精制的渐近导数(通常称为精确的渐近学),其中$ \ zeta_n $代表$ \ zeta_n $误差概率的大多数代表性亚指数项。
translated by 谷歌翻译
Continual Learning, also known as Lifelong or Incremental Learning, has recently gained renewed interest among the Artificial Intelligence research community. Recent research efforts have quickly led to the design of novel algorithms able to reduce the impact of the catastrophic forgetting phenomenon in deep neural networks. Due to this surge of interest in the field, many competitions have been held in recent years, as they are an excellent opportunity to stimulate research in promising directions. This paper summarizes the ideas, design choices, rules, and results of the challenge held at the 3rd Continual Learning in Computer Vision (CLVision) Workshop at CVPR 2022. The focus of this competition is the complex continual object detection task, which is still underexplored in literature compared to classification tasks. The challenge is based on the challenge version of the novel EgoObjects dataset, a large-scale egocentric object dataset explicitly designed to benchmark continual learning algorithms for egocentric category-/instance-level object understanding, which covers more than 1k unique main objects and 250+ categories in around 100k video frames.
translated by 谷歌翻译
The fifth generation of the Radio Access Network (RAN) has brought new services, technologies, and paradigms with the corresponding societal benefits. However, the energy consumption of 5G networks is today a concern. In recent years, the design of new methods for decreasing the RAN power consumption has attracted interest from both the research community and standardization bodies, and many energy savings solutions have been proposed. However, there is still a need to understand the power consumption behavior of state-ofthe-art base station architectures, such as multi-carrier active antenna units (AAUs), as well as the impact of different network parameters. In this paper, we present a power consumption model for 5G AAUs based on artificial neural networks. We demonstrate that this model achieves good estimation performance, and it is able to capture the benefits of energy saving when dealing with the complexity of multi-carrier base stations architectures. Importantly, multiple experiments are carried out to show the advantage of designing a general model able to capture the power consumption behaviors of different types of AAUs. Finally, we provide an analysis of the model scalability and the training data requirements.
translated by 谷歌翻译
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.
translated by 谷歌翻译
移动网络第五代(5G)的能源消耗是电信行业的主要关注点之一。但是,目前没有一种评估5G基站(BSS)功耗的准确且可进行的方法。在本文中,我们提出了一个新颖的模型,以实现5G多载波BSS功耗的现实表征,该模型以大型数据收集活动为基础。首先,我们定义了允许对多个5G BS产品进行建模的机器学习体系结构。然后,我们利用该框架收集的知识来得出一个现实且可分析的功耗模型,这可以帮助推动理论分析以及功能标准化,开发和优化框架。值得注意的是,我们证明了这种模型具有很高的精度,并且能够捕获节能机制的好处。我们认为,该分析模型是理解5G BSS功耗的基本工具,并准确地优化了网络能源效率。
translated by 谷歌翻译
用于图像分割的深卷卷卷神经网络不会明确学习标签结构,并且可能会在类似树状结构(例如气道或血管)分割的圆柱形结构中产生不正确的结构(例如,具有断开的圆柱形结构)的分割。在本文中,我们提出了一种新型的标签改进方法,以从初始分割中纠正此类错误,并隐含地包含有关标签结构的信息。该方法具有两个新颖的部分:1)生成合成结构误差的模型,以及2)产生合成分割(带有误差)的标签外观仿真网络,其外观与实际初始分段相似。使用这些合成分割和原始图像,对标签改进网络进行了训练,以纠正错误并改善初始分割。该方法对两个分割任务进行了验证:来自胸部计算机断层扫描(CT)扫描和大脑3D CT血管造影(CTA)图像的脑血管分割的气道分割。在这两种应用中,我们的方法都大大优于标准的3D U-NET和其他先前的改进方法。当使用其他未标记的数据进行模型培训时,改进甚至更大。在消融研究中,我们证明了所提出方法的不同组成部分的值。
translated by 谷歌翻译
点云过滤和正常估计是3D场中的两个基本研究问题。现有方法通常会单独执行正常的估计和过滤,并且经常表现出对噪声和/或无法保留尖锐几何特征(例如角和边缘)的敏感性。在本文中,我们提出了一种新颖的深度学习方法,以共同估计正态和过滤点云。我们首先引入了一个基于3D补丁的对比学习框架,并以噪声损坏为增强,以训练能够生成点云斑块的忠实表示的功能编码器,同时保持噪音的强大功能。这些表示由简单的回归网络消耗,并通过新的关节损失进行监督,同时估算用于过滤贴片中心的点正常和位移。实验结果表明,我们的方法同时支持这两个任务,并保留尖锐的功能和细节。通常,它在这两个任务上都胜过最先进的技术。
translated by 谷歌翻译
从电影心脏磁共振(CMR)成像中恢复心脏的3D运动可以评估区域心肌功能,对于理解和分析心血管疾病很重要。但是,3D心脏运动估计是具有挑战性的,因为获得的Cine CMR图像通常是2D切片,它限制了对整个平面运动的准确估计。为了解决这个问题,我们提出了一个新颖的多视图运动估计网络(Mulvimotion),该网络集成了以短轴和长轴平面获取的2D Cine CMR图像,以学习心脏的一致性3D运动场。在提出的方法中,构建了一个混合2D/3D网络,以通过从多视图图像中学习融合表示形式来生成密集的3D运动场。为了确保运动估计在3D中保持一致,在训练过程中引入了形状正则化模块,其中利用了来自多视图图像的形状信息,以提供3D运动估计的弱监督。我们对来自英国生物银行研究的580名受试者的2D Cine CMR图像进行了广泛评估,用于左心室心肌的3D运动跟踪。实验结果表明,该方法在定量和定性上优于竞争方法。
translated by 谷歌翻译
密切的人类机器人互动(HRI),尤其是在工业场景中,已经对结合人类和机器人技能的优势进行了广泛的研究。对于有效的HRI,应质疑当前可用的人机通信媒体或工具的有效性,并应探讨新的交流方式。本文提出了一个模块化体系结构,允许人类操作员通过不同的方式与机器人互动。特别是,我们使用智能手表和平板电脑分别实施了架构来分别处理手势和触摸屏输入。最后,我们在这两种方式之间进行了比较用户体验研究。
translated by 谷歌翻译
通过离散采样观测来建模连续的动力系统是数据科学中的一个基本问题。通常,这种动力学是非本地过程随时间不可或缺的结果。因此,这些系统是用插差分化方程(IDE)建模的;构成积分和差分组件的微分方程的概括。例如,大脑动力学不是通过微分方程来准确模拟的,因为它们的行为是非马克维亚的,即动态是部分由历史决定的。在这里,我们介绍了神经IDE(NIDE),该框架使用神经网络建模IDE的普通和组成部分。我们在几个玩具和大脑活动数据集上测试NIDE,并证明NIDE的表现优于其他模型,包括神经ODE。这些任务包括时间外推,以及从看不见的初始条件中预测动态,我们在自由行为的小鼠中测试了全皮质活动记录。此外,我们表明,NIDE可以通过学识渊博的整体操作员将动力学分解为马尔可夫和非马克维亚成分,我们在氯胺酮的fMRI脑活动记录中测试了动力学。最后,整体操作员的整体提供了一个潜在空间,可深入了解潜在的动态,我们在宽阔的大脑成像记录上证明了这一点。总体而言,NIDE是一种新颖的方法,可以通过神经网络对复杂的非本地动力学进行建模。
translated by 谷歌翻译