本文提出了一个紧凑的系统OpenPneu，以支持软机器人多腔的气动驱动。系统中使用微型泵来生成气流，因此不需要额外的输入，因为需要压缩空气。我们的系统执行模块化设计以提供良好的可扩展性，这已在具有十个空气通道的原型上证明。OpenPNEU的每个空气通道都配备了通货膨胀和通气功能，可提供从正到负的全范围压力供应，最大流速为1.7 L/min。我们的系统内置了对压力的高精度闭环控制，以实现稳定而有效的动态性能。提供了Python中的开源控制接口和API。我们还证明了OpenPneu在三个软机器人系统上的功能，最多10个腔室。

Basecalling is an essential step in nanopore sequencing analysis where the raw signals of nanopore sequencers are converted into nucleotide sequences, i.e., reads. State-of-the-art basecallers employ complex deep learning models to achieve high basecalling accuracy. This makes basecalling computationally-inefficient and memory-hungry; bottlenecking the entire genome analysis pipeline. However, for many applications, the majority of reads do no match the reference genome of interest (i.e., target reference) and thus are discarded in later steps in the genomics pipeline, wasting the basecalling computation. To overcome this issue, we propose TargetCall, the first fast and widely-applicable pre-basecalling filter to eliminate the wasted computation in basecalling. TargetCall's key idea is to discard reads that will not match the target reference (i.e., off-target reads) prior to basecalling. TargetCall consists of two main components: (1) LightCall, a lightweight neural network basecaller that produces noisy reads; and (2) Similarity Check, which labels each of these noisy reads as on-target or off-target by matching them to the target reference. TargetCall filters out all off-target reads before basecalling; and the highly-accurate but slow basecalling is performed only on the raw signals whose noisy reads are labeled as on-target. Our thorough experimental evaluations using both real and simulated data show that TargetCall 1) improves the end-to-end basecalling performance of the state-of-the-art basecaller by 3.31x while maintaining high (98.88%) sensitivity in keeping on-target reads, 2) maintains high accuracy in downstream analysis, 3) precisely filters out up to 94.71% of off-target reads, and 4) achieves better performance, sensitivity, and generality compared to prior works. We freely open-source TargetCall at https://github.com/CMU-SAFARI/TargetCall.

An approach to evolutionary ensemble learning for classification is proposed in which boosting is used to construct a stack of programs. Each application of boosting identifies a single champion and a residual dataset, i.e. the training records that thus far were not correctly classified. The next program is only trained against the residual, with the process iterating until some maximum ensemble size or no further residual remains. Training against a residual dataset actively reduces the cost of training. Deploying the ensemble as a stack also means that only one classifier might be necessary to make a prediction, so improving interpretability. Benchmarking studies are conducted to illustrate competitiveness with the prediction accuracy of current state-of-the-art evolutionary ensemble learning algorithms, while providing solutions that are orders of magnitude simpler. Further benchmarking with a high cardinality dataset indicates that the proposed method is also more accurate and efficient than XGBoost.

Effective conservation of maritime environments and wildlife management of endangered species require the implementation of efficient, accurate and scalable solutions for environmental monitoring. Ecoacoustics offers the advantages of non-invasive, long-duration sampling of environmental sounds and has the potential to become the reference tool for biodiversity surveying. However, the analysis and interpretation of acoustic data is a time-consuming process that often requires a great amount of human supervision. This issue might be tackled by exploiting modern techniques for automatic audio signal analysis, which have recently achieved impressive performance thanks to the advances in deep learning research. In this paper we show that convolutional neural networks can indeed significantly outperform traditional automatic methods in a challenging detection task: identification of dolphin whistles from underwater audio recordings. The proposed system can detect signals even in the presence of ambient noise, at the same time consistently reducing the likelihood of producing false positives and false negatives. Our results further support the adoption of artificial intelligence technology to improve the automatic monitoring of marine ecosystems.

While large-scale sequence modeling from offline data has led to impressive performance gains in natural language and image generation, directly translating such ideas to robotics has been challenging. One critical reason for this is that uncurated robot demonstration data, i.e. play data, collected from non-expert human demonstrators are often noisy, diverse, and distributionally multi-modal. This makes extracting useful, task-centric behaviors from such data a difficult generative modeling problem. In this work, we present Conditional Behavior Transformers (C-BeT), a method that combines the multi-modal generation ability of Behavior Transformer with future-conditioned goal specification. On a suite of simulated benchmark tasks, we find that C-BeT improves upon prior state-of-the-art work in learning from play data by an average of 45.7%. Further, we demonstrate for the first time that useful task-centric behaviors can be learned on a real-world robot purely from play data without any task labels or reward information. Robot videos are best viewed on our project website: https://play-to-policy.github.io

基于自我监督的基于学习的预科可以使用小标签的数据集开发可靠和广义的深度学习模型，从而减轻了标签生成的负担。本文旨在评估基于CL的预处理对可转介的性能与非转介糖尿病性视网膜病（DR）分类的影响。我们已经开发了一个基于CL的框架，具有神经风格转移（NST）增强，以生成具有更好表示和初始化的模型，以检测颜色底面图像中的DR。我们将CL预估计的模型性能与用成像网权重预测的两个最先进的基线模型进行了比较。我们通过减少标记的训练数据（降至10％）进一步研究模型性能，以测试使用小标签数据集训练模型的鲁棒性。该模型在EYEPACS数据集上进行了培训和验证，并根据芝加哥伊利诺伊大学（UIC）的临床数据进行了独立测试。与基线模型相比，我们的CL预处理的基础网模型具有更高的AUC（CI）值（0.91（0.898至0.930），在UIC数据上为0.80（0.783至0.820）和0.83（0.783至0.820）（0.801至0.853）。在10％标记的培训数据时，在UIC数据集上测试时，基线模型中的FoldusNet AUC为0.81（0.78至0.84），比0.58（0.56至0.64）和0.63（0.56至0.64）和0.63（0.60至0.66）。基于CL的NST预处理可显着提高DL分类性能，帮助模型良好（可从Eyepacs转移到UIC数据），并允许使用小的带注释的数据集进行培训，从而减少临床医生的地面真相注释负担。

在过去的几年中，未配对的图像DeNoising取得了有希望的发展。无论表现如何，方法都倾向于严重依赖潜在的噪声属性或任何并不总是实用的假设。另外，如果我们可以从结构的角度而不是噪声统计数据解决问题，那么我们可以实现更强大的解决方案。通过这种动机，我们提出了一个自制的剥夺计划，该计划是不成功的，依赖于空间降解，然后进行正规化的精炼。我们的方法比以前的方法显示出显着改善，并且在不同的数据域上表现出一致的性能。

剖面隐藏的马尔可夫模型（PHMM）广泛用于许多生物信息学应用中，以准确识别生物学序列（例如DNA或蛋白质序列）之间的相似性。 PHMM使用常用和高度精确的方法（称为Baum-Welch算法）来计算这些相似性。但是，Baum-Welch算法在计算上很昂贵，现有作品为固定的PHMM设计提供了软件或仅硬件解决方案。当我们分析最先进的作品时，我们发现迫切需要灵活，高性能和节能的硬件软件共同设计，以有效地有效地解决所有主要效率低下的效率PHMM的Baum-Welch算法。我们提出了APHMM，这是第一个灵活的加速框架，可以显着减少PHMM的Baum-Welch算法的计算和能量开销。 APHMM利用硬件软件共同设计来解决Baum-Welch算法中的主要效率低下，通过1）设计灵活的硬件来支持不同的PHMMS设计，2）利用可预测的数据依赖性模式，并使用chip Memory的片段记忆，使用纪念活动技术，memoigience Memoriques，Memoigience Memoriques，Memoigient， 3）通过基于硬件的过滤器快速消除可忽略的计算，4）最小化冗余计算。我们在专用硬件和2）GPU的软件优化方面实现了我们的1）硬件软件优化，以为PHMM提供首个灵活的Baum-Welch加速器。与Baum-Welch算法的CPU，GPU和FPGA实现相比，APHMM提供的显着加速度为15.55 x-260.03x，1.83x-5.34x和27.97倍，分别为27.97倍。 APHMM的表现优于三个重要的生物信息学应用程序的最新CPU实现，1）错误校正，2）蛋白质家族搜索和3）多个序列对齐，比1.29x-59.94x，1.03x-1.75x和分别为1.03x-1.95x。

类激活图（CAM）有助于制定显着图，有助于解释深度神经网络的预测。基于梯度的方法通常比视力解释性的其他分支更快，并且独立于人类的指导。类似CAM的研究的性能取决于管理模型的层响应以及梯度的影响。典型的面向梯度的CAM研究依赖加权聚合来进行显着图估计，通过将梯度图投影到单权重值中，这可能导致过度的广义显着图。为了解决此问题，我们使用全球指导图来纠正显着性估计过程中加权聚合操作，在这种情况下，结果解释是相对干净的ER且特定于实例的。我们通过在特征图及其相应的梯度图之间执行元素乘法来获得全局引导图。为了验证我们的研究，我们将拟议的研究与八个不同的显着性可视化器进行了比较。此外，我们使用七个常用的评估指标进行定量比较。提出的方案比ImageNet，MS-Coco 14和Pascal VOC 2012数据集的测试图像取得了重大改进。

在许多计算机视觉子域中，图像降级仍然是一个具有挑战性的问题。最近的研究表明，在有监督的环境中取得了重大改进。但是，很少有挑战（例如空间忠诚度和类似卡通的平滑度）仍未解决或果断地忽略。我们的研究提出了一个简单而有效的架构，用于解决上述问题的降级问题。所提出的体系结构重新审视了模块化串联的概念，而不是长时间和更深的级联连接，以恢复给定图像的更清洁近似。我们发现不同的模块可以捕获多功能表示形式，而串联表示为低级图像恢复创造了更丰富的子空间。所提出的架构的参数数量仍然小于以前的大多数网络的数量，并且仍然对当前最新网络进行了重大改进。