Humans and animals can learn new skills after practicing for a few hours, while current reinforcement learning algorithms require a large amount of data to achieve good performances. Recent model-based approaches show promising results by reducing the number of necessary interactions with the environment to learn a desirable policy. However, these methods require biological implausible ingredients, such as the detailed storage of older experiences, and long periods of offline learning. The optimal way to learn and exploit word-models is still an open question. Taking inspiration from biology, we suggest that dreaming might be an efficient expedient to use an inner model. We propose a two-module (agent and model) spiking neural network in which "dreaming" (living new experiences in a model-based simulated environment) significantly boosts learning. We also explore "planning", an online alternative to dreaming, that shows comparable performances. Importantly, our model does not require the detailed storage of experiences, and learns online the world-model and the policy. Moreover, we stress that our network is composed of spiking neurons, further increasing the biological plausibility and implementability in neuromorphic hardware.
translated by 谷歌翻译
We extend our recently proposed Deep Learning-aided many-body dispersion (DNN-MBD) model to quadrupole polarizability (Q) terms using a generalized Random Phase Approximation (RPA) formalism, thus enabling the inclusion of van der Waals contributions beyond dipole. The resulting DNN-MBDQ model only relies on ab initio-derived quantities as the introduced quadrupole polarizabilities are recursively retrieved from dipole ones, in turn modelled via the Tkatchenko-Scheffler method. A transferable and efficient deep-neuronal network (DNN) provides atom in molecule volumes, while a single range-separation parameter is used to couple the model to Density Functional Theory (DFT). Since it can be computed at a negligible cost, the DNN-MBDQ approach can be coupled with DFT functionals such as PBE,PBE0 and B86bPBE (dispersionless). The DNN-MBQ-corrected functionals reach chemical accuracy while exhibiting lower errors compared to the DNN-MBD dipole-only counterparts as well as to other MBD-based dispersion correction models where the accuracy gain can reache up to 45%.
translated by 谷歌翻译
Did you know that over 70 million of Dota2 players have their in-game data freely accessible? What if such data is used in malicious ways? This paper is the first to investigate such a problem. Motivated by the widespread popularity of video games, we propose the first threat model for Attribute Inference Attacks (AIA) in the Dota2 context. We explain how (and why) attackers can exploit the abundant public data in the Dota2 ecosystem to infer private information about its players. Due to lack of concrete evidence on the efficacy of our AIA, we empirically prove and assess their impact in reality. By conducting an extensive survey on $\sim$500 Dota2 players spanning over 26k matches, we verify whether a correlation exists between a player's Dota2 activity and their real-life. Then, after finding such a link ($p\!<\!0.01$ and $\rho>0.3$), we ethically perform diverse AIA. We leverage the capabilities of machine learning to infer real-life attributes of the respondents of our survey by using their publicly available in-game data. Our results show that, by applying domain expertise, some AIA can reach up to 98% precision and over 90% accuracy. This paper hence raises the alarm on a subtle, but concrete threat that can potentially affect the entire competitive gaming landscape. We alerted the developers of Dota2.
translated by 谷歌翻译
意图发现是NLP的一项基本任务,它与各种工业应用越来越相关(Quarteroni 2018)。主要的挑战在于需要从投入性话语中识别出新颖的范围。在此,我们提出了Z-Bert-A,这是一种依赖变压器结构的两阶段方法(Vaswani等人,2017; Devlin等人,2018年),用适配器进行了微调(Pfeiffer等,2020),,),等等。最初接受了自然语言推断(NLI)的培训,后来在零射击设置中申请了未知的内部分类。在我们的评估中,我们首先在已知类别的自适应微调后分析模型的质量。其次,我们将其性能铸造意图分类评估为NLI任务。最后,我们在看不见的类别上测试了模型的零射击性能,以表明Z-Bert-A可以通过产生与地面真实者的语义相似(即使不是平等)的意图,如何有效地执行周期发现。我们的实验表明,Z-Bert-A在两个零射击设置中的表现如何超过各种基线:已知意图分类和看不见的意图发现。拟议的管道具有广泛应用于各种客户服务应用程序的潜力。它可以使用轻巧的模型来实现自动化动态分流,该模型与大型语言模型不同,可以轻松地在各种业务场景中进行部署和缩放。尤其是在考虑具有有限的硬件可用性和性能的设置时,必须进行原始或资源云部署低的设置。 Z-Bert-A可以从单一话语中预测新颖的意图,代表了一种创新的意图发现方法,从而使在线一代的新颖意图能够。该管道可作为可安装的Python软件包获得以下链接:https://github.com/gt4sd/zberta。
translated by 谷歌翻译
无监督的域适应性(UDA)旨在减少训练和测试数据之间的域间隙,并在大多数情况下以离线方式进行。但是,在部署过程中可能会连续且不可预测地发生域的变化(例如,天气变化突然变化)。在这种情况下,深度神经网络见证了准确性的急剧下降,离线适应可能不足以对比。在本文中,我们解决了在线域适应(ONDA)进行语义细分。我们设计了一条可逐步或突然转移的域转移的管道,在多雨和有雾的情况下,我们对其进行了评估。我们的实验表明,我们的框架可以有效地适应部署期间的新域,而不受灾难性遗忘以前的域的影响。
translated by 谷歌翻译
我们考虑基于模型的多代理增强学习,其中环境过渡模型未知,只能通过与环境的昂贵互动来学习。我们提出了H-MARL(幻觉多代理增强学习),这是一种新型样本算法,可以有效地平衡探索,即学习环境和剥削,即在基本的一般及其Markov游戏中实现良好的平衡性能。 H-MARL围绕未知过渡模型建立高概率的置信区间,并根据新观察到的数据顺序更新它们。使用这些,它为每轮计算平衡策略的代理商构建了一个乐观的幻觉游戏。我们考虑一般的统计模型(例如高斯流程,深层合奏等)和政策类(例如,深神经网络),理论上通过限制了代理人的动态遗憾来分析我们的方法。此外,我们为基础马尔可夫游戏的平衡提供了融合率。我们对自主驾驶模拟基准测试的实验证明了我们的方法。 H-MARL与环境进行了几次相互作用后,学习成功的平衡策略,与非最佳探索方法相比,可以显着提高性能。
translated by 谷歌翻译
如今,人们在网上平台上生成并分享大量内容(例如,社交网络,博客)。 2021年,每分钟为119亿日常积极的Facebook用户发布了大约15万张照片。内容主持人不断监控这些在线平台,以防止扩散不适当的内容(例如,讨厌语音,裸露图像)。基于深度学习(DL)的进步,自动内容主持人(ACM)帮助人类主持人处理高数据量。尽管他们的优势,攻击者可以利用DL组件的弱点(例如,预处理,模型)来影响其性能。因此,攻击者可以利用这些技术来通过逃避ACM来扩散不适当的内容。在这项工作中,我们提出了CAPTCHA攻击(CAPA),这是一种允许用户通过逃避ACM控件来扩散不恰当的文本的对抗技术。通过生成自定义文本CAPTCHAS的CAPA,利用ACM的粗心设计实现和内部程序漏洞。我们对现实世界ACM的攻击进行了测试,结果证实了我们简单但有效攻击的凶猛,在大多数情况下达到了100%的逃避成功。与此同时,我们展示了设计CAPA缓解,在CAPTCHAS研究区开辟了新挑战的困难。
translated by 谷歌翻译
压缩传感(CS)一直在加速磁共振成像(MRI)采集过程中的关键作用。随着人工智能的复苏,深神经网络和CS算法正在集成以重新定义快速MRI的领域。过去几年目睹了基于深度学习的CS技术的复杂性,多样性和表现的大量增长,这些技术致力于快速MRI。在该荟萃分析中,我们系统地审查了快速MRI的深度学习的CS技术,描述了关键模型设计,突出突破,并讨论了有希望的方向。我们还介绍了一个综合分析框架和分类系统,以评估深度学习在基于CS的加速度的MRI的关键作用。
translated by 谷歌翻译
本文介绍了学习迭代查询细化的元策略的设计代理的首先成功步骤。我们的方法使用机器读取来指导从聚合搜索结果中选择细化项。然后,使用简单但有效的搜索操作员能够赋予代理,以对查询和搜索结果发挥细粒度和透明控制。我们开发一种新颖的方式来发电综合搜索会话,它通过(自我)监督学习来利用基于变压器的语言模型的力量。我们还提出了一种强化学习代理,具有动态约束的动作,从划痕中了解互动搜索策略。我们使用传统的基于术语的BM25排名函数获得与最近神经方法相当的检索和回答质量性能。我们对搜索政策进行了深入的分析。
translated by 谷歌翻译