This case study investigates the extent to which a language model (GPT-2) is able to capture native speakers' intuitions about implicit causality in a sentence completion task. We first reproduce earlier results (showing lower surprisal values for pronouns that are congruent with either the subject or object, depending on which one corresponds to the implicit causality bias of the verb), and then examine the effects of gender and verb frequency on model performance. Our second study examines the reasoning ability of GPT-2: is the model able to produce more sensible motivations for why the subject VERBed the object if the verbs have stronger causality biases? We also developed a methodology to avoid human raters being biased by obscenities and disfluencies generated by the model.
translated by 谷歌翻译
In this paper, we propose a novel technique, namely INVALIDATOR, to automatically assess the correctness of APR-generated patches via semantic and syntactic reasoning. INVALIDATOR reasons about program semantic via program invariants while it also captures program syntax via language semantic learned from large code corpus using the pre-trained language model. Given a buggy program and the developer-patched program, INVALIDATOR infers likely invariants on both programs. Then, INVALIDATOR determines that a APR-generated patch overfits if: (1) it violates correct specifications or (2) maintains errors behaviors of the original buggy program. In case our approach fails to determine an overfitting patch based on invariants, INVALIDATOR utilizes a trained model from labeled patches to assess patch correctness based on program syntax. The benefit of INVALIDATOR is three-fold. First, INVALIDATOR is able to leverage both semantic and syntactic reasoning to enhance its discriminant capability. Second, INVALIDATOR does not require new test cases to be generated but instead only relies on the current test suite and uses invariant inference to generalize the behaviors of a program. Third, INVALIDATOR is fully automated. We have conducted our experiments on a dataset of 885 patches generated on real-world programs in Defects4J. Experiment results show that INVALIDATOR correctly classified 79% overfitting patches, accounting for 23% more overfitting patches being detected by the best baseline. INVALIDATOR also substantially outperforms the best baselines by 14% and 19% in terms of Accuracy and F-Measure, respectively.
translated by 谷歌翻译
Modern deep neural networks have achieved superhuman performance in tasks from image classification to game play. Surprisingly, these various complex systems with massive amounts of parameters exhibit the same remarkable structural properties in their last-layer features and classifiers across canonical datasets. This phenomenon is known as "Neural Collapse," and it was discovered empirically by Papyan et al. \cite{Papyan20}. Recent papers have theoretically shown the global solutions to the training network problem under a simplified "unconstrained feature model" exhibiting this phenomenon. We take a step further and prove the Neural Collapse occurrence for deep linear network for the popular mean squared error (MSE) and cross entropy (CE) loss. Furthermore, we extend our research to imbalanced data for MSE loss and present the first geometric analysis for Neural Collapse under this setting.
translated by 谷歌翻译
In heterogeneous networks (HetNets), the overlap of small cells and the macro cell causes severe cross-tier interference. Although there exist some approaches to address this problem, they usually require global channel state information, which is hard to obtain in practice, and get the sub-optimal power allocation policy with high computational complexity. To overcome these limitations, we propose a multi-agent deep reinforcement learning (MADRL) based power control scheme for the HetNet, where each access point makes power control decisions independently based on local information. To promote cooperation among agents, we develop a penalty-based Q learning (PQL) algorithm for MADRL systems. By introducing regularization terms in the loss function, each agent tends to choose an experienced action with high reward when revisiting a state, and thus the policy updating speed slows down. In this way, an agent's policy can be learned by other agents more easily, resulting in a more efficient collaboration process. We then implement the proposed PQL in the considered HetNet and compare it with other distributed-training-and-execution (DTE) algorithms. Simulation results show that our proposed PQL can learn the desired power control policy from a dynamic environment where the locations of users change episodically and outperform existing DTE MADRL algorithms.
translated by 谷歌翻译
Air pollution is an emerging problem that needs to be solved especially in developed and developing countries. In Vietnam, air pollution is also a concerning issue in big cities such as Hanoi and Ho Chi Minh cities where air pollution comes mostly from vehicles such as cars and motorbikes. In order to tackle the problem, the paper focuses on developing a solution that can estimate the emitted PM2.5 pollutants by counting the number of vehicles in the traffic. We first investigated among the recent object detection models and developed our own traffic surveillance system. The observed traffic density showed a similar trend to the measured PM2.5 with a certain lagging in time, suggesting a relation between traffic density and PM2.5. We further express this relationship with a mathematical model which can estimate the PM2.5 value based on the observed traffic density. The estimated result showed a great correlation with the measured PM2.5 plots in the urban area context.
translated by 谷歌翻译
According to the World Federation of the Deaf, more than two hundred sign languages exist. Therefore, it is challenging to understand deaf individuals, even proficient sign language users, resulting in a barrier between the deaf community and the rest of society. To bridge this language barrier, we propose a novel multilingual communication system, namely MUGCAT, to improve the communication efficiency of sign language users. By converting recognized specific hand gestures into expressive pictures, which is universal usage and language independence, our MUGCAT system significantly helps deaf people convey their thoughts. To overcome the limitation of sign language usage, which is mostly impossible to translate into complete sentences for ordinary people, we propose to reconstruct meaningful sentences from the incomplete translation of sign language. We also measure the semantic similarity of generated sentences with fragmented recognized hand gestures to keep the original meaning. Experimental results show that the proposed system can work in a real-time manner and synthesize exquisite stunning illustrations and meaningful sentences from a few hand gestures of sign language. This proves that our MUGCAT has promising potential in assisting deaf communication.
translated by 谷歌翻译
3D hand pose estimation from RGB images suffers from the difficulty of obtaining the depth information. Therefore, a great deal of attention has been spent on estimating 3D hand pose from 2D hand joints. In this paper, we leverage the advantage of spatial-temporal Graph Convolutional Neural Networks and propose LG-Hand, a powerful method for 3D hand pose estimation. Our method incorporates both spatial and temporal dependencies into a single process. We argue that kinematic information plays an important role, contributing to the performance of 3D hand pose estimation. We thereby introduce two new objective functions, Angle and Direction loss, to take the hand structure into account. While Angle loss covers locally kinematic information, Direction loss handles globally kinematic one. Our LG-Hand achieves promising results on the First-Person Hand Action Benchmark (FPHAB) dataset. We also perform an ablation study to show the efficacy of the two proposed objective functions.
translated by 谷歌翻译
预测基金绩效对投资者和基金经理都是有益的,但这是一项艰巨的任务。在本文中,我们测试了深度学习模型是否比传统统计技术更准确地预测基金绩效。基金绩效通常通过Sharpe比率进行评估,该比例代表了风险调整的绩效,以确保基金之间有意义的可比性。我们根据每月收益率数据序列数据计算了年度夏普比率,该数据的时间序列数据为600多个投资于美国上市大型股票的开放式共同基金投资。我们发现,经过现代贝叶斯优化训练的长期短期记忆(LSTM)和封闭式复发单元(GRUS)深度学习方法比传统统计量相比,预测基金的Sharpe比率更高。结合了LSTM和GRU的预测的合奏方法,可以实现所有模型的最佳性能。有证据表明,深度学习和结合能提供有希望的解决方案,以应对基金绩效预测的挑战。
translated by 谷歌翻译
构建静态呼叫图需要在健全和精度之间进行权衡。不幸的是,用于构建呼叫图的程序分析技术通常不精确。为了解决这个问题,研究人员最近提出了通过机器学习为静态分析构建的后处理呼叫图所授权的呼叫图。机器学习模型的构建是为了通过在随机森林分类器中提取结构特征来捕获呼叫图中的信息。然后,它消除了预测为误报的边缘。尽管机器学习模型显示了改进,但它们仍然受到限制,因为它们不考虑源代码语义,因此通常无法有效地区分真实和误报。在本文中,我们提出了一种新颖的呼叫图修剪技术AutoRoprouner,用于通过统计语义和结构分析消除呼叫图中的假阳性。给定一个由传统静态分析工具构建的呼叫图,AutoProuner采用基于变压器的方法来捕获呼叫者与呼叫图中每个边缘相关的呼叫者和Callee函数之间的语义关系。为此,AutoProuner微型调节模型是在大型语料库上预先训练的代码模型,以根据其语义的描述表示源代码。接下来,该模型用于从与呼叫图中的每个边缘相关的功能中提取语义特征。 AutoProuner使用这些语义功能以及从呼叫图提取的结构特征通过馈送前向神经网络分类。我们在现实世界程序的基准数据集上进行的经验评估表明,AutoProuner的表现优于最先进的基线,从而改善了F量级,在识别静态呼叫图中识别错误阳性边缘方面,高达13%。
translated by 谷歌翻译
数十年来,计算机系统持有大量个人数据。一方面,这种数据丰度允许在人工智能(AI),尤其是机器学习(ML)模型中突破。另一方面,它可能威胁用户的隐私并削弱人类与人工智能之间的信任。最近的法规要求,可以从一般情况下从计算机系统中删除有关用户的私人信息,特别是根据要求从ML模型中删除(例如,“被遗忘的权利”)。虽然从后端数据库中删除数据应该很简单,但在AI上下文中,它不够,因为ML模型经常“记住”旧数据。现有的对抗攻击证明,我们可以从训练有素的模型中学习私人会员或培训数据的属性。这种现象要求采用新的范式,即机器学习,以使ML模型忘记了特定的数据。事实证明,由于缺乏共同的框架和资源,最近在机器上学习的工作无法完全解决问题。在本调查文件中,我们试图在其定义,场景,机制和应用中对机器进行彻底的研究。具体而言,作为最先进的研究的类别集合,我们希望为那些寻求机器未学习的入门及其各种表述,设计要求,删除请求,算法和用途的人提供广泛的参考。 ML申请。此外,我们希望概述范式中的关键发现和趋势,并突出显示尚未看到机器无法使用的新研究领域,但仍可以受益匪浅。我们希望这项调查为ML研究人员以及寻求创新隐私技术的研究人员提供宝贵的参考。我们的资源是在https://github.com/tamlhp/awesome-machine-unlearning上。
translated by 谷歌翻译