已经引入了生成流量网络(GFlowNETS)作为在主动学习背景下采样多样化候选的方法,具有培训目标,其使它们与给定奖励功能成比例地进行比例。在本文中,我们显示了许多额外的GFLOWN的理论特性。它们可用于估计联合概率分布和一些变量未指定的相应边际分布,并且特别感兴趣地,可以代表像集合和图形的复合对象的分布。 Gflownets摊销了通常通过计算昂贵的MCMC方法在单个但训练有素的生成通行证中进行的工作。它们还可用于估计分区功能和自由能量,给定子集(子图)的超标(超图)的条件概率,以及给定集合(图)的所有超标仪(超图)的边际分布。我们引入了熵和相互信息估计的变体,从帕累托前沿采样,与奖励最大化策略的连接,以及随机环境的扩展,连续动作和模块化能量功能。
translated by 谷歌翻译
由于其宽度趋于无穷大,如果梯度下降下的深度神经网络的行为可以简化和可预测(例如,如果神经切线核(NTK)给出,则如果适当地进行了参数化(例如,NTK参数化)。但是,我们表明,神经网络的标准和NTK参数化不接受可以学习特征的无限宽度限制,这对于训练和转移学习至关重要。我们对标准参数化提出了简单的修改,以允许在极限内进行特征学习。使用 * Tensor程序 *技术,我们为此类限制提供了明确的公式。在Word2Vec和Omniglot上通过MAML进行的几杆学习,这是两个依赖特征学习的规范任务,我们准确地计算了这些限制。我们发现它们的表现都优于NTK基准和有限宽度网络,后者接近无限宽度的特征学习表现,随着宽度的增加。更普遍地,我们对神经网络参数化的自然空间进行分类,该空间概括了标准,NTK和平均场参数化。我们显示1)该空间中的任何参数化都可以接受特征学习或具有内核梯度下降给出的无限宽度训练动力学,但并非两者兼而有之; 2)可以使用Tensor程序技术计算任何此类无限宽度限制。可以在github.com/edwardjhu/tp4上找到我们的实验代码。
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
Point-of-Care Ultrasound (POCUS) refers to clinician-performed and interpreted ultrasonography at the patient's bedside. Interpreting these images requires a high level of expertise, which may not be available during emergencies. In this paper, we support POCUS by developing classifiers that can aid medical professionals by diagnosing whether or not a patient has pneumothorax. We decomposed the task into multiple steps, using YOLOv4 to extract relevant regions of the video and a 3D sparse coding model to represent video features. Given the difficulty in acquiring positive training videos, we trained a small-data classifier with a maximum of 15 positive and 32 negative examples. To counteract this limitation, we leveraged subject matter expert (SME) knowledge to limit the hypothesis space, thus reducing the cost of data collection. We present results using two lung ultrasound datasets and demonstrate that our model is capable of achieving performance on par with SMEs in pneumothorax identification. We then developed an iOS application that runs our full system in less than 4 seconds on an iPad Pro, and less than 8 seconds on an iPhone 13 Pro, labeling key regions in the lung sonogram to provide interpretable diagnoses.
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
具有多模式传感(AIPPMS)的自适应信息路径计划(AIPPMS)考虑了配备多个传感器的代理商的问题,每个传感器具有不同的感应精度和能量成本。代理商的目标是探索环境并在未知的,部分可观察到的环境中受到其资源约束的信息。先前的工作集中在不太一般的适应性信息路径计划(AIPP)问题上,该问题仅考虑了代理人运动对收到的观察结果的影响。 AIPPMS问题通过要求代理的原因共同出现感应和移动的影响,同时平衡资源约束与信息目标,从而增加了额外的复杂性。我们将AIPPMS问题作为一种信念马尔可夫决策过程,并具有高斯流程信念,并使用在线计划中使用顺序的贝叶斯优化方法来解决它。我们的方法始终优于以前的AIPPMS解决方案,这几乎将几乎每个实验中获得的平均奖励增加了一倍,同时还将根平方的错误在环境信念中减少了50%。我们完全开放我们的实施方式,以帮助进一步开发和比较。
translated by 谷歌翻译
结肠镜检查被广泛认为是早期检测结直肠癌(CRC)的金标准程序。分割对于两种重要的临床应用,即病变检测和分类很有价值,提供了提高准确性和鲁棒性的手段。结肠镜检查中息肉的手动分割是耗时的。结果,使用深度学习(DL)进行息肉的自动化已经变得很重要。但是,基于DL的解决方案可能容易受到过度拟合的影响,因此无法推广到不同结肠镜捕获的图像。最新的基于变压器的语义分割的体系结构既实现更高的性能又比替代方案更好,但是通常可以预测$ \ frac {h} {4} \ times \ times \ frac {w} {4} {4} $ apatial dimensions的分割图h \ times w $输入图像。为此,我们提出了一种用于全尺寸分割的新体系结构,该结构利用了变压器在主要分支中提取最重要的特征的优势,同时用二级全卷积分支全面预测其限制了其局限性。然后将两个分支的最终功能融合,以最终预测$ h \ times w $分段地图。我们在KVASIR-SEG和CVC-ClinicDB数据集基准上都证明了我们方法相对于MDICE,MIOU,MPRECISION和MRECALL METICS的最先进性能。此外,我们在每个数据集上训练模型,并对另一个数据集进行评估以证明其出色的概括性能。
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
低计数正电子发射断层扫描(PET)数据的图像重建是具有挑战性的。内核方法通过在迭代宠物图像重建的前向模型中结合图像先前信息来解决挑战。已经开发出并证明了内核预期的最大化(KEM)算法是有效且易于实施的。进一步改进内核方法的常见方法是添加明确的正则化,但是导致复杂的优化问题。在本文中,我们通过使用深度系数来提出内核方法的隐含正则化,其使用卷积神经网络表示宠物前进模型中的内核系数图像。为解决基于最大似然性的神经网络的重建问题,我们应用优化转移原理来推导神经KEM算法。算法的每次迭代包括两个单独的步骤:从投影数据的图像更新的KEM步骤和图像域中的深度学习步骤,用于使用神经网络更新内核系数图像。这种优化算法保证单调地增加数据可能性。计算机模拟和实际患者数据的结果表明神经KEM可以优于现有的KEM和深度图像的先前方法。
translated by 谷歌翻译
虽然已知存在强烈相关的抗病毒发动机的组,但目前有限地了解如何或为什么这些相关性所在的理解。使用代表杀毒扫描数据十年的2500万致毒素报告的语料库,我们挑战普遍的智慧,即这些相关性主要来自“一阶”互动,例如杀毒供应商复制领先供应商标签。我们介绍时间秩-1相似性矩阵分解(R1SM-T),以研究这些相关性的起源,并模拟杀毒发动机之间的共识如何随时间变化。我们揭示了一流的相互作用,并不像以前认为杀毒相关的那么多的行为,并且杀毒发动机之间的关系具有高度挥发性。我们提出了根据我们的研究结果需要未来学习和考虑的项目的建议。
translated by 谷歌翻译