驾驶行为是道路崩溃和事故的主要原因之一，可以通过识别和最小化攻击性驾驶行为来减少这些原因。本研究确定了当不同情况下的驾驶员（匆忙，精神冲突，报复）开始积极推动时的时间戳。需要观察者（真实或虚拟）来检查驾驶行为以发现攻击性驾驶场合;我们通过使用智能手机的GPS传感器来检测位置并每三分钟分类驱动器的驾驶行为来克服这个问题。为了检测我们数据集中的TimeSeries模式，我们使用RNN（GRU，LSTM）算法来识别驾驶过程中的模式。该算法与道路，车辆，位置或驾驶员特性无关。我们得出结论，三分钟（或更多）的驾驶（120秒的GPS数据）足以识别驾驶员行为。结果显示出高精度和高F1分数。

Fast timescale state estimation for a large power system can be challenging if the sensors producing the measurements are few in number. This is particularly true for doing time-synchronized state estimation for a transmission system that has minimal phasor measurement unit (PMU) coverage. This paper proposes a Deep Neural network-based State Estimator (DeNSE) to overcome this extreme unobservability problem. For systems in which the existing PMU infrastructure is not able to bring the estimation errors within acceptable limits using the DeNSE, a data-driven incremental PMU placement methodology is also introduced. The practical utility of the proposed approach is demonstrated by considering topology changes, non-Gaussian measurement noise, bad data detection and correction, and large system application.

链路预测是预测知识图的实体之间缺失关系的任务。最近的链路预测工作已经尝试通过在神经网络架构中使用更多层来提供增加链路预测精度的模型。在本文中，我们提出了一种精炼知识图的新方法，从而可以使用相对快速的翻译模型更准确地执行链路预测操作。翻译链接预测模型，如Transe，Transh，Transd，而不是深度学习方法的复杂性较小。我们的方法使用知识图中的关系和实体的层次结构将实体信息作为辅助节点添加到图形中，并将它们连接到包含在其层级中的该信息的节点。我们的实验表明，我们的方法可以显着提高H @ 10的翻译链路预测方法的性能，MRR，MRR。

Interview has been regarded as one of the most crucial step for recruitment. To fully prepare for the interview with the recruiters, job seekers usually practice with mock interviews between each other. However, such a mock interview with peers is generally far away from the real interview experience: the mock interviewers are not guaranteed to be professional and are not likely to behave like a real interviewer. Due to the rapid growth of online recruitment in recent years, recruiters tend to have online interviews, which makes it possible to collect real interview data from real interviewers. In this paper, we propose a novel application named EZInterviewer, which aims to learn from the online interview data and provides mock interview services to the job seekers. The task is challenging in two ways: (1) the interview data are now available but still of low-resource; (2) to generate meaningful and relevant interview dialogs requires thorough understanding of both resumes and job descriptions. To address the low-resource challenge, EZInterviewer is trained on a very small set of interview dialogs. The key idea is to reduce the number of parameters that rely on interview dialogs by disentangling the knowledge selector and dialog generator so that most parameters can be trained with ungrounded dialogs as well as the resume data that are not low-resource. Evaluation results on a real-world job interview dialog dataset indicate that we achieve promising results to generate mock interviews. With the help of EZInterviewer, we hope to make mock interview practice become easier for job seekers.

Unsupervised learning-based anomaly detection in latent space has gained importance since discriminating anomalies from normal data becomes difficult in high-dimensional space. Both density estimation and distance-based methods to detect anomalies in latent space have been explored in the past. These methods prove that retaining valuable properties of input data in latent space helps in the better reconstruction of test data. Moreover, real-world sensor data is skewed and non-Gaussian in nature, making mean-based estimators unreliable for skewed data. Again, anomaly detection methods based on reconstruction error rely on Euclidean distance, which does not consider useful correlation information in the feature space and also fails to accurately reconstruct the data when it deviates from the training distribution. In this work, we address the limitations of reconstruction error-based autoencoders and propose a kernelized autoencoder that leverages a robust form of Mahalanobis distance (MD) to measure latent dimension correlation to effectively detect both near and far anomalies. This hybrid loss is aided by the principle of maximizing the mutual information gain between the latent dimension and the high-dimensional prior data space by maximizing the entropy of the latent space while preserving useful correlation information of the original data in the low-dimensional latent space. The multi-objective function has two goals -- it measures correlation information in the latent feature space in the form of robust MD distance and simultaneously tries to preserve useful correlation information from the original data space in the latent space by maximizing mutual information between the prior and latent space.

We present Second Thought, a new learning paradigm that enables language models (LMs) to re-align with human values. By modeling the chain-of-edits between value-unaligned and value-aligned text, with LM fine-tuning and additional refinement through reinforcement learning, Second Thought not only achieves superior performance in three value alignment benchmark datasets but also shows strong human-value transfer learning ability in few-shot scenarios. The generated editing steps also offer better interpretability and ease for interactive error correction. Extensive human evaluations further confirm its effectiveness.

Solving portfolio management problems using deep reinforcement learning has been getting much attention in finance for a few years. We have proposed a new method using experts signals and historical price data to feed into our reinforcement learning framework. Although experts signals have been used in previous works in the field of finance, as far as we know, it is the first time this method, in tandem with deep RL, is used to solve the financial portfolio management problem. Our proposed framework consists of a convolutional network for aggregating signals, another convolutional network for historical price data, and a vanilla network. We used the Proximal Policy Optimization algorithm as the agent to process the reward and take action in the environment. The results suggested that, on average, our framework could gain 90 percent of the profit earned by the best expert.

Practically all of the planning research is limited to states represented in terms of Boolean and numeric state variables. Many practical problems, for example, planning inside complex software systems, require far more complex data types, and even real-world planning in many cases requires concepts such as sets of objects, which are not convenient to express in modeling languages with scalar types only. In this work, we investigate a modeling language for complex software systems, which supports complex data types such as sets, arrays, records, and unions. We give a reduction of a broad range of complex data types and their operations to Boolean logic, and then map this representation further to PDDL to be used with domain-independent PDDL planners. We evaluate the practicality of this approach, and provide solutions to some of the issues that arise in the PDDL translation.

Neural operators, which emerge as implicit solution operators of hidden governing equations, have recently become popular tools for learning responses of complex real-world physical systems. Nevertheless, the majority of neural operator applications has thus far been data-driven, which neglects the intrinsic preservation of fundamental physical laws in data. In this paper, we introduce a novel integral neural operator architecture, to learn physical models with fundamental conservation laws automatically guaranteed. In particular, by replacing the frame-dependent position information with its invariant counterpart in the kernel space, the proposed neural operator is by design translation- and rotation-invariant, and consequently abides by the conservation laws of linear and angular momentums. As applications, we demonstrate the expressivity and efficacy of our model in learning complex material behaviors from both synthetic and experimental datasets, and show that, by automatically satisfying these essential physical laws, our learned neural operator is not only generalizable in handling translated and rotated datasets, but also achieves state-of-the-art accuracy and efficiency as compared to baseline neural operator models.

Recent trends in language modeling have focused on increasing performance through scaling, and have resulted in an environment where training language models is out of reach for most researchers and practitioners. While most in the community are asking how to push the limits of extreme computation, we ask the opposite question: How far can we get with a single GPU in just one day? We investigate the downstream performance achievable with a transformer-based language model trained completely from scratch with masked language modeling for a single day on a single consumer GPU. Aside from re-analyzing nearly all components of the pretraining pipeline for this scenario and providing a modified pipeline with performance close to BERT, we investigate why scaling down is hard, and which modifications actually improve performance in this scenario. We provide evidence that even in this constrained setting, performance closely follows scaling laws observed in large-compute settings. Through the lens of scaling laws, we categorize a range of recent improvements to training and architecture and discuss their merit and practical applicability (or lack thereof) for the limited compute setting.