ECG数据库通常由于正常的心电图和异常病例的稀缺性而高度不平衡。因此，经过不平衡数据集培训的深度学习分类器通常表现不佳，尤其是在次要课程上。一种解决方案是使用生成对抗网络（GAN）生成逼真的合成ECG信号，以增强数据集的不平衡数据集。在这项研究中，我们首次将条件GAN与WGAN-GAN结合在一起，并以1D形式开发了AC-WGAN-GP，以应用于MIT-BIH心律失常数据集。我们研究了数据增强对心律失常分类的影响。我们采用了两个模型进行心电图生成：（i）无条件的gan； Wasserstein gan具有梯度罚款（WGAN-GP）在每个班级上都受过训练； （ii）有条件的gan；一个辅助分类器WGAN-GP（AC-WGAN-GP）模型均在所有类别上训练，然后用于在所有类别中生成合成节拍。每种情况下定义了两种情况：（a）未经检查；使用了所有生成的合成节拍，并且（b）筛选；基于其动态时间翘曲（DTW）到指定模板，仅选择并使用了一部分生成的节拍。在每个增强数据集和性能指标（精确/召回/F1得分微型和宏观水平，混淆矩阵，多层级别的Precision-Recall Precall curves）中，对最先进的重新NET分类器（ECGRESNET34）进行了培训（precision/Recemision/Recker/F1得分微观和宏观分数）。与未表现不平衡案件的案件相比。我们还使用了简单的度量净改进。这三个指标始终显示出净改进（总和次级和次级），无条件的GAN具有原始生成的数据（未筛选）可创造最佳改进。

由于异常情况的稀缺性，心电图（ECG）数据集往往受到高度不平衡的。此外，由于隐私问题，使用真正的患者的心电图是高度监管的。因此，总是需要更多的ECG数据，特别是对于自动诊断机器学习模型的培训，这在培训在平衡数据集时更好地执行。我们研究了从生成的对抗网络（GAN）家庭的5种不同模型的合成ECG生成能力，并比较了它们的表演，焦点仅在正常的心脏周期上。动态时间翘曲（DTW），FR \'echet和欧几里德距离功能用于定量测量性能。提出并应用了评估生成节拍的五种不同方法。我们还提出了3个新概念（阈值，接受的节拍和生产率），并将其与上述方法一起作为一种系统的方式，以便在模型之间进行比较。结果表明，所有测试模型都可以在一定程度上成功地产生具有高相似性的可接受的心跳，在形态特征中具有高相似性，并且可能所有这些都可以使用它们来增强不平衡的数据集。然而，产生的节拍的目视检查有利于Bilstm-DC Gan和Wan，因为它们产生统计上更可接受的节拍。此外，关于生产率，经典GaN优越，生产率72％。

We demonstrate a proof-of-concept of a large language model conducting corporate lobbying related activities. We use an autoregressive large language model (OpenAI's text-davinci-003) to determine if proposed U.S. Congressional bills are relevant to specific public companies and provide explanations and confidence levels. For the bills the model deems as relevant, the model drafts a letter to the sponsor of the bill in an attempt to persuade the congressperson to make changes to the proposed legislation. We use hundreds of ground-truth labels of the relevance of a bill to a company to benchmark the performance of the model, which outperforms the baseline of predicting the most common outcome of irrelevance. However, we test the ability to determine the relevance of a bill with the previous OpenAI GPT-3 model (text-davinci-002), which was state-of-the-art on many language tasks until text-davinci-003 was released on November 28, 2022. The performance of text-davinci-002 is worse than simply always predicting that a bill is irrelevant to a company. These results suggest that, as large language models continue to improve core natural language understanding capabilities, performance on corporate lobbying related tasks will continue to improve. We then discuss why this could be problematic for societal-AI alignment.

Previous work has shown the potential of deep learning to predict renal obstruction using kidney ultrasound images. However, these image-based classifiers have been trained with the goal of single-visit inference in mind. We compare methods from video action recognition (i.e. convolutional pooling, LSTM, TSM) to adapt single-visit convolutional models to handle multiple visit inference. We demonstrate that incorporating images from a patient's past hospital visits provides only a small benefit for the prediction of obstructive hydronephrosis. Therefore, inclusion of prior ultrasounds is beneficial, but prediction based on the latest ultrasound is sufficient for patient risk stratification.

Microswimmers can acquire information on the surrounding fluid by sensing mechanical queues. They can then navigate in response to these signals. We analyse this navigation by combining deep reinforcement learning with direct numerical simulations to resolve the hydrodynamics. We study how local and non-local information can be used to train a swimmer to achieve particular swimming tasks in a non-uniform flow field, in particular a zig-zag shear flow. The swimming tasks are (1) learning how to swim in the vorticity direction, (2) the shear-gradient direction, and (3) the shear flow direction. We find that access to lab frame information on the swimmer's instantaneous orientation is all that is required in order to reach the optimal policy for (1,2). However, information on both the translational and rotational velocities seem to be required to achieve (3). Inspired by biological microorganisms we also consider the case where the swimmers sense local information, i.e. surface hydrodynamic forces, together with a signal direction. This might correspond to gravity or, for micro-organisms with light sensors, a light source. In this case, we show that the swimmer can reach a comparable level of performance as a swimmer with access to lab frame variables. We also analyse the role of different swimming modes, i.e. pusher, puller, and neutral swimmers.

Quantifying motion in 3D is important for studying the behavior of humans and other animals, but manual pose annotations are expensive and time-consuming to obtain. Self-supervised keypoint discovery is a promising strategy for estimating 3D poses without annotations. However, current keypoint discovery approaches commonly process single 2D views and do not operate in the 3D space. We propose a new method to perform self-supervised keypoint discovery in 3D from multi-view videos of behaving agents, without any keypoint or bounding box supervision in 2D or 3D. Our method uses an encoder-decoder architecture with a 3D volumetric heatmap, trained to reconstruct spatiotemporal differences across multiple views, in addition to joint length constraints on a learned 3D skeleton of the subject. In this way, we discover keypoints without requiring manual supervision in videos of humans and rats, demonstrating the potential of 3D keypoint discovery for studying behavior.

With water quality management processes, identifying and interpreting relationships between features, such as location and weather variable tuples, and water quality variables, such as levels of bacteria, is key to gaining insights and identifying areas where interventions should be made. There is a need for a search process to identify the locations and types of phenomena that are influencing water quality and a need to explain why the quality is being affected and which factors are most relevant. This paper addresses both of these issues through the development of a process for collecting data for features that represent a variety of variables over a spatial region, which are used for training and inference, and analysing the performance of the features using the model and Shapley values. Shapley values originated in cooperative game theory and can be used to aid in the interpretation of machine learning results. Evaluations are performed using several machine learning algorithms and water quality data from the Dublin Grand Canal basin.

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.

Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a a single "generic" user will confer more general alignment. Here, we embrace the heterogeneity of human preferences to consider a different challenge: how might a machine help people with diverse views find agreement? We fine-tune a 70 billion parameter LLM to generate statements that maximize the expected approval for a group of people with potentially diverse opinions. Human participants provide written opinions on thousands of questions touching on moral and political issues (e.g., "should we raise taxes on the rich?"), and rate the LLM's generated candidate consensus statements for agreement and quality. A reward model is then trained to predict individual preferences, enabling it to quantify and rank consensus statements in terms of their appeal to the overall group, defined according to different aggregation (social welfare) functions. The model produces consensus statements that are preferred by human users over those from prompted LLMs (>70%) and significantly outperforms a tight fine-tuned baseline that lacks the final ranking step. Further, our best model's consensus statements are preferred over the best human-generated opinions (>65%). We find that when we silently constructed consensus statements from only a subset of group members, those who were excluded were more likely to dissent, revealing the sensitivity of the consensus to individual contributions. These results highlight the potential to use LLMs to help groups of humans align their values with one another.

Inverse kinematics of many common types of robot manipulators may be decomposed into canonical subproblems. This paper presents new solution methods to six subproblems using a linear algebra approach. The first three subproblems, called the Paden-Kahan subproblems, are Subproblem 1: angle between a vector on the edge of a cone and a point, Subproblem 2: intersections between two cones, and Subproblem 3: intersections between a cone and a sphere. The other three subproblems, which have not been extensively covered in the literature, are Subproblem 4: intersections between a cone and a plane, Subproblem 5: intersections among three cones, and Subproblem 6: intersections in a system of four cones. We present algebraic solutions and geometric interpretations for each subproblem and provide computational performance comparisons. Our approach also finds the least-squares solutions for Subproblems 1-4 when the exact solution does not exist. We show that almost all 6-dof all revolute (6R) robots with known closed-form solutions may be solved using the subproblem decomposition method. For a general 6R robot, subproblem decomposition reduces finding all solutions to a search on a circle or a 2D torus. The software code is available on a publicly accessible repository.