我们开发了BenchPress,这是第一个用于编译器的ML基准生成器,它是在源代码的功能空间表示中可检测的。卧推通过在空序列或现有序列的任何部分中添加新代码,通过共同观察其左和右下文,从而综合编译函数,从而达到出色的汇编速率。卧推操纵基准的生成迈向了所需的目标特征,这对于最先进的合成器(或实际上人类)不可能达到。与(a)clgen-最先进的ML合成器,(b)Clsmith Fuzzer,(c)Srciror Mutator或(d)人写代码相比来自Github。 Benchpress是第一个通过主动学习搜索功能空间的生成器,以生成可以改善下游任务的基准。我们展示了Grewe's等人如何使用台式。与其他技术相比,CPU与GPU启发式模型在台式基准测试中进行训练时可以获得更高的加速。卧推是一个强大的代码生成器:其生成的样品以86%的速度编译,而Clgen的2.33%则以86%的速度编译。从一个空的固定输入开始,台式比CLGEN产生的10倍,可汇编的OpenCL基准测试,这些基准比Clgen更大,并且更具多样性。
translated by 谷歌翻译
自动语音识别(ASR)系统普遍存在,特别是在国内电器语音导航和语音控制的应用中。 ASR的计算核心是已被证明易于对抗性扰动的深神经网络(DNN);容易被攻击者滥用生成恶意输出。为了帮助测试ASR的正确性,我们提出了自动生成BlackBox(无关的DNN)的技术,跨ASR可移植的未标准的对抗性攻击。在对冲ASR测试的大部分工作中侧重于针对目标攻击,即给定输出文本生成音频样本。目标技术不可移植,定制到特定ASR内的DNN(白箱)的结构。相比之下,我们的方法攻击在大多数ASR中共享的ASR管道的信号处理阶段。另外,我们确保通过使用维持人类感知阈值低于人类感知阈值的信号来操纵声学信号,确保产生的对抗性音频样本没有人类的声音差异。我们使用三个流行的ASR和三个输入音频数据集使用输出文本的指标来评估我们技术的可移植性和有效性,以及不同ASR上的原始音频的相似性和攻击成功率。我们发现我们的测试技术是跨ASR的便携式携带的,并具有对原始音频的高成功率,WERS和相似性的对抗的音频样本。
translated by 谷歌翻译
Can we take a recurrent neural network (RNN) trained to translate between languages and augment it to support a new natural language without retraining the model from scratch? Can we fix the faulty behavior of the RNN by replacing portions associated with the faulty behavior? Recent works on decomposing a fully connected neural network (FCNN) and convolutional neural network (CNN) into modules have shown the value of engineering deep models in this manner, which is standard in traditional SE but foreign for deep learning models. However, prior works focus on the image-based multiclass classification problems and cannot be applied to RNN due to (a) different layer structures, (b) loop structures, (c) different types of input-output architectures, and (d) usage of both nonlinear and logistic activation functions. In this work, we propose the first approach to decompose an RNN into modules. We study different types of RNNs, i.e., Vanilla, LSTM, and GRU. Further, we show how such RNN modules can be reused and replaced in various scenarios. We evaluate our approach against 5 canonical datasets (i.e., Math QA, Brown Corpus, Wiki-toxicity, Clinc OOS, and Tatoeba) and 4 model variants for each dataset. We found that decomposing a trained model has a small cost (Accuracy: -0.6%, BLEU score: +0.10%). Also, the decomposed modules can be reused and replaced without needing to retrain.
translated by 谷歌翻译
Fairness of machine learning (ML) software has become a major concern in the recent past. Although recent research on testing and improving fairness have demonstrated impact on real-world software, providing fairness guarantee in practice is still lacking. Certification of ML models is challenging because of the complex decision-making process of the models. In this paper, we proposed Fairify, an SMT-based approach to verify individual fairness property in neural network (NN) models. Individual fairness ensures that any two similar individuals get similar treatment irrespective of their protected attributes e.g., race, sex, age. Verifying this fairness property is hard because of the global checking and non-linear computation nodes in NN. We proposed sound approach to make individual fairness verification tractable for the developers. The key idea is that many neurons in the NN always remain inactive when a smaller part of the input domain is considered. So, Fairify leverages whitebox access to the models in production and then apply formal analysis based pruning. Our approach adopts input partitioning and then prunes the NN for each partition to provide fairness certification or counterexample. We leveraged interval arithmetic and activation heuristic of the neurons to perform the pruning as necessary. We evaluated Fairify on 25 real-world neural networks collected from four different sources, and demonstrated the effectiveness, scalability and performance over baseline and closely related work. Fairify is also configurable based on the domain and size of the NN. Our novel formulation of the problem can answer targeted verification queries with relaxations and counterexamples, which have practical implications.
translated by 谷歌翻译
Machine Learning (ML) software has been widely adopted in modern society, with reported fairness implications for minority groups based on race, sex, age, etc. Many recent works have proposed methods to measure and mitigate algorithmic bias in ML models. The existing approaches focus on single classifier-based ML models. However, real-world ML models are often composed of multiple independent or dependent learners in an ensemble (e.g., Random Forest), where the fairness composes in a non-trivial way. How does fairness compose in ensembles? What are the fairness impacts of the learners on the ultimate fairness of the ensemble? Can fair learners result in an unfair ensemble? Furthermore, studies have shown that hyperparameters influence the fairness of ML models. Ensemble hyperparameters are more complex since they affect how learners are combined in different categories of ensembles. Understanding the impact of ensemble hyperparameters on fairness will help programmers design fair ensembles. Today, we do not understand these fully for different ensemble algorithms. In this paper, we comprehensively study popular real-world ensembles: bagging, boosting, stacking and voting. We have developed a benchmark of 168 ensemble models collected from Kaggle on four popular fairness datasets. We use existing fairness metrics to understand the composition of fairness. Our results show that ensembles can be designed to be fairer without using mitigation techniques. We also identify the interplay between fairness composition and data characteristics to guide fair ensemble design. Finally, our benchmark can be leveraged for further research on fair ensembles. To the best of our knowledge, this is one of the first and largest studies on fairness composition in ensembles yet presented in the literature.
translated by 谷歌翻译
不断增加的材料科学文章使得很难从已发表的文献中推断化学结构 - 培训关系。我们使用自然语言处理(NLP)方法从聚合物文献的摘要中自动提取材料属性数据。作为我们管道的组成部分,我们使用240万材料科学摘要培训了一种语言模型的材料,该材料模型在用作文本编码器时,在五分之三命名实体识别数据集中的其他基线模型都优于其他基线模型。使用此管道,我们在60小时内从约130,000个摘要中获得了约300,000个物质记录。分析了提取的数据,分析了各种应用,例如燃料电池,超级电容器和聚合物太阳能电池,以恢复非平凡的见解。通过我们的管道提取的数据可通过https://polymerscholar.org的Web平台提供,该数据可方便地定位摘要中记录的材料属性数据。这项工作证明了自动管道的可行性,该管道从已发布的文献开始,并以一组完整的提取物质属性信息结束。
translated by 谷歌翻译
自2016年成立以来,Alexa奖计划使数百名大学生能够通过Socialbot Grand Challenge探索和竞争以发展对话代理商。挑战的目的是建立能够与人类在流行主题上连贯而诱人的代理人20分钟,同时达到至少4.0/5.0的平均评分。但是,由于对话代理商试图帮助用户完成日益复杂的任务,因此需要新的对话AI技术和评估平台。成立于2021年的Alexa奖Taskbot Challenge建立在Socialbot Challenge的成功基础上,通过引入交互式协助人类进行现实世界烹饪和做自己动手做的任务的要求,同时同时使用语音和视觉方式。这项挑战要求TaskBots识别和理解用户的需求,识别和集成任务和域知识,并开发新的方式,不分散用户的注意力,而不必分散他们的任务,以及其他挑战。本文概述了Taskbot挑战赛,描述了使用Cobot Toolkit提供给团队提供的基础架构支持,并总结了参与团队以克服研究挑战所采取的方法。最后,它分析了比赛第一年的竞争任务机器人的性能。
translated by 谷歌翻译
口服食物挑战(OFC)对于准确诊断患者的食物过敏至关重要。但是,患者不愿接受OFC,对于那些这样做的患者,在农村/社区医疗保健环境中,对过敏症患者的使用率有限。通过机器学习方法对OFC结果的预测可以促进在家中食品过敏原的删除,在OFC中改善患者和医师的舒适度,并通过最大程度地减少执行的OFC的数量来节省医疗资源。临床数据是从共同接受1,284个OFC的1,12例患者那里收集的,包括临床因素,包括血清特异性IgE,总IgE,皮肤刺测试(SPTS),症状,性别和年龄。使用这些临床特征,构建了机器学习模型,以预测花生,鸡蛋和牛奶挑战的结果。每种过敏原的最佳性能模型是使用凹入和凸内核(LUCCK)方法创建的,该方法在曲线(AUC)(AUC)下分别用于花生,鸡蛋和牛奶OFC预测为0.76、0.68和0.70, 。通过Shapley添加说明(SHAP)的模型解释表明,特定的IgE以及SPTS的Wheal和Flare值高度预测了OFC结果。该分析的结果表明,机器学习有可能预测OFC结果,并揭示了相关的临床因素进行进一步研究。
translated by 谷歌翻译
一个沿着城市街道行走的人试图对世界各个方面进行建模,这很快就会被许多商店,汽车和人们遵循自己的复杂且难以理解的动态所淹没。在这种环境中的探索和导航是一项日常任务,不需要大量精神资源。是否可以将这种感官信息的消防软管转变为最小的潜在状态,这是代理在世界上成功采取行动的必要和足够的?我们具体地提出了这个问题,并提出了可控制的状态发现算法(AC-State),该算法具有理论保证,并且实际上被证明可以发现\ textit {最小可控的潜在状态},其中包含所有用于控制控制的信息代理,同时完全丢弃所有无关的信息。该算法由一个具有信息瓶颈的多步逆模型(预测遥远观察结果的动作)组成。 AC-State可以在没有奖励或示威的情况下实现本地化,探索和导航。我们证明了在三个领域中发现可控潜在状态的发现:将机器人组分散注意力(例如,照明条件和背景变化),与其他代理商一起在迷宫中进行探索,并在Matterport House Simulator中导航。
translated by 谷歌翻译
准确地检测出具有不同语义和协变量转移相对于分布的数据(ID)数据的分布外(OOD)数据对于部署安全可靠的模型至关重要。当处理高度结果应用(例如医学成像,自动驾驶汽车等)时,情况尤其如此。目的是设计一个可以接受ID数据有意义变化的检测器,同时还拒绝了OOD制度的示例。在实践中,可以通过使用适当的评分函数(例如能量)来实现一致性来实现此双重目标,并校准检测器以拒绝一组策划的OOD数据(称为离群曝光或不久的OE)。尽管OE方法被广泛采用,但由于现实世界情景的不可预测性,组装代表性的OOD数据集既昂贵又具有挑战性,因此最新设计了无OE探测器的趋势。在本文中,我们做出了一个令人惊讶的发现,即控制对ID变化的概括和暴露于不同(合成)异常值的示例对于同时改善语义和模态转移检测至关重要。与现有方法相反,我们的方法样本在潜在空间中嵌入式体系,并通过负数据扩展构建异常示例。通过一项关于医学成像基准(MedMnist,ISIC2019和NCT)的严格实证研究,我们在语义和模态转移下的现有无OE,OOD检测方法上表现出显着的性能增长(AUROC中的15美元\%-35 \%$)。
translated by 谷歌翻译