450万小时的英语演讲从10个不同的10个不同来源，跨越高达10亿参数的不同来源，我们探索了自动语音识别的规模前沿。我们提出了数据选择技术，以有效地缩放培训数据，以找到大规模数据集中最有价值的样本。为了有效地进行模型尺寸，我们利用各种优化，例如稀疏传感器丢失和模型分片。通过培训1-10B参数通用英语ASR模型，我们将语音识别性能的限制推动在许多域中。此外，我们的模型学习强大的语音表示，在新域名和言语方面具有零和少量功能，超出了多个内部和公共基准的先前结果。对于由于脑损伤而具有障碍的扬声器，我们最好的零射击和少量射频分别在Aphasiabank测试集中实现了22％和60％，同时在公共社交媒体视频中实现了最佳性能。此外，相同的通用模型在SPGISPeech Financial-Domain数据集上达到了500倍的域内数据等效性能。

Targeted syntactic evaluations of language models ask whether models show stable preferences for syntactically acceptable content over minimal-pair unacceptable inputs. Most targeted syntactic evaluation datasets ask models to make these judgements with just a single context-free sentence as input. This does not match language models' training regime, in which input sentences are always highly contextualized by the surrounding corpus. This mismatch raises an important question: how robust are models' syntactic judgements in different contexts? In this paper, we investigate the stability of language models' performance on targeted syntactic evaluations as we vary properties of the input context: the length of the context, the types of syntactic phenomena it contains, and whether or not there are violations of grammaticality. We find that model judgements are generally robust when placed in randomly sampled linguistic contexts. However, they are substantially unstable for contexts containing syntactic structures matching those in the critical test content. Among all tested models (GPT-2 and five variants of OPT), we significantly improve models' judgements by providing contexts with matching syntactic structures, and conversely significantly worsen them using unacceptable contexts with matching but violated syntactic structures. This effect is amplified by the length of the context, except for unrelated inputs. We show that these changes in model performance are not explainable by simple features matching the context and the test inputs, such as lexical overlap and dependency overlap. This sensitivity to highly specific syntactic features of the context can only be explained by the models' implicit in-context learning abilities.

We design and implement an adaptive machine learning equalizer that alternates multiple linear and nonlinear computational layers on an FPGA. On-chip training via gradient backpropagation is shown to allow for real-time adaptation to time-varying channel impairments.

Enhancing resilience in distributed networks in the face of malicious agents is an important problem for which many key theoretical results and applications require further development and characterization. This work focuses on the problem of distributed optimization in multi-agent cyberphysical systems, where a legitimate agent's dynamic is influenced both by the values it receives from potentially malicious neighboring agents, and by its own self-serving target function. We develop a new algorithmic and analytical framework to achieve resilience for the class of problems where stochastic values of trust between agents exist and can be exploited. In this case we show that convergence to the true global optimal point can be recovered, both in mean and almost surely, even in the presence of malicious agents. Furthermore, we provide expected convergence rate guarantees in the form of upper bounds on the expected squared distance to the optimal value. Finally, we present numerical results that validate the analytical convergence guarantees we present in this paper even when the malicious agents compose the majority of agents in the network.

Video synthesis methods rapidly improved in recent years, allowing easy creation of synthetic humans. This poses a problem, especially in the era of social media, as synthetic videos of speaking humans can be used to spread misinformation in a convincing manner. Thus, there is a pressing need for accurate and robust deepfake detection methods, that can detect forgery techniques not seen during training. In this work, we explore whether this can be done by leveraging a multi-modal, out-of-domain backbone trained in a self-supervised manner, adapted to the video deepfake domain. We propose FakeOut; a novel approach that relies on multi-modal data throughout both the pre-training phase and the adaption phase. We demonstrate the efficacy and robustness of FakeOut in detecting various types of deepfakes, especially manipulations which were not seen during training. Our method achieves state-of-the-art results in cross-manipulation and cross-dataset generalization. This study shows that, perhaps surprisingly, training on out-of-domain videos (i.e., videos with no speaking humans), can lead to better deepfake detection systems. Code is available on GitHub.

Effective conservation of maritime environments and wildlife management of endangered species require the implementation of efficient, accurate and scalable solutions for environmental monitoring. Ecoacoustics offers the advantages of non-invasive, long-duration sampling of environmental sounds and has the potential to become the reference tool for biodiversity surveying. However, the analysis and interpretation of acoustic data is a time-consuming process that often requires a great amount of human supervision. This issue might be tackled by exploiting modern techniques for automatic audio signal analysis, which have recently achieved impressive performance thanks to the advances in deep learning research. In this paper we show that convolutional neural networks can indeed significantly outperform traditional automatic methods in a challenging detection task: identification of dolphin whistles from underwater audio recordings. The proposed system can detect signals even in the presence of ambient noise, at the same time consistently reducing the likelihood of producing false positives and false negatives. Our results further support the adoption of artificial intelligence technology to improve the automatic monitoring of marine ecosystems.

We derive a learning framework to generate routing/pickup policies for a fleet of vehicles tasked with servicing stochastically appearing requests on a city map. We focus on policies that 1) give rise to coordination amongst the vehicles, thereby reducing wait times for servicing requests, 2) are non-myopic, considering a-priori unknown potential future requests, and 3) can adapt to changes in the underlying demand distribution. Specifically, we are interested in adapting to fluctuations of actual demand conditions in urban environments, such as on-peak vs. off-peak hours. We achieve this through a combination of (i) online play, a lookahead optimization method that improves the performance of rollout methods via an approximate policy iteration step, and (ii) an offline approximation scheme that allows for adapting to changes in the underlying demand model. In particular, we achieve adaptivity of our learned policy to different demand distributions by quantifying a region of validity using the q-valid radius of a Wasserstein Ambiguity Set. We propose a mechanism for switching the originally trained offline approximation when the current demand is outside the original validity region. In this case, we propose to use an offline architecture, trained on a historical demand model that is closer to the current demand in terms of Wasserstein distance. We learn routing and pickup policies over real taxicab requests in downtown San Francisco with high variability between on-peak and off-peak hours, demonstrating the ability of our method to adapt to real fluctuation in demand distributions. Our numerical results demonstrate that our method outperforms rollout-based reinforcement learning, as well as several benchmarks based on classical methods from the field of operations research.

In this study, we propose a lung nodule detection scheme which fully incorporates the clinic workflow of radiologists. Particularly, we exploit Bi-Directional Maximum intensity projection (MIP) images of various thicknesses (i.e., 3, 5 and 10mm) along with a 3D patch of CT scan, consisting of 10 adjacent slices to feed into self-distillation-based Multi-Encoders Network (MEDS-Net). The proposed architecture first condenses 3D patch input to three channels by using a dense block which consists of dense units which effectively examine the nodule presence from 2D axial slices. This condensed information, along with the forward and backward MIP images, is fed to three different encoders to learn the most meaningful representation, which is forwarded into the decoded block at various levels. At the decoder block, we employ a self-distillation mechanism by connecting the distillation block, which contains five lung nodule detectors. It helps to expedite the convergence and improves the learning ability of the proposed architecture. Finally, the proposed scheme reduces the false positives by complementing the main detector with auxiliary detectors. The proposed scheme has been rigorously evaluated on 888 scans of LUNA16 dataset and obtained a CPM score of 93.6\%. The results demonstrate that incorporating of bi-direction MIP images enables MEDS-Net to effectively distinguish nodules from surroundings which help to achieve the sensitivity of 91.5% and 92.8% with false positives rate of 0.25 and 0.5 per scan, respectively.

我们为对抗性多机器人群众跨任务中的决策制定开发了一个有弹性的二进制假设测试框架。该框架利用机器人之间的随机信任观察，以在集中式融合中心（FC）中得出可进行的弹性决策，即使I）在网络中存在恶意机器人，其数量可能大于合法机器人的数量，并且II ）FC使用所有机器人的一次性噪声测量。我们得出两种算法来实现这一目标。第一个是两个阶段方法（2SA），该方法基于收到的信任观察估算机器人的合法性，并证明在最严重的恶意攻击中可最大程度地减少检测错误的可能性。在这里，恶意机器人的比例是已知但任意的。对于不明的恶意机器人，我们开发了对抗性的广义似然比测试（A-GLRT），该测试（A-GLRT）都使用报告的机器人测量和信任观察来估计机器人的可信赖性，其报告策略以及同时的正确假设。我们利用特殊的问题结构表明，尽管有几个未知的问题参数，但这种方法仍然可以计算处理。我们在硬件实验中部署了这两种算法，其中一组机器人会在模拟道路网络上进行交通状况的人群，但仍会受到SYBIL攻击的方式。我们从实际通信信号中提取每个机器人的信任观察结果，这些信号提供有关发件人独特性的统计信息。我们表明，即使恶意机器人在大多数情况下，FC也可以将检测误差的可能性降低到2SA和A-GLRT的30.5％和29％。

了解强化学习（RL）代理的新兴行为可能很困难，因为这种代理通常使用高度复杂的决策程序在复杂的环境中进行训练。这引起了RL中解释性的多种方法，旨在调和可能在主体行为与观察者预期的行为之间产生的差异。最近的方法取决于域知识，这可能并非总是可用的，分析代理商的策略，或者是对基础环境的特定要素的分析，通常被建模为马尔可夫决策过程（MDP）。我们的主要主张是，即使基本的MDP尚不完全了解（例如，尚未准确地了解过渡概率），也没有由代理商维护（即，在使用无模型方法时），但仍可以利用它为自动生成解释。为此，我们建议使用以前在文献中使用的正式MDP抽象和转换来加快寻找最佳策略的搜索，以自动产生解释。由于这种转换通常基于环境的符号表示，因此它们可能代表了预期和实际代理行为之间差距的有意义的解释。我们正式定义了这个问题，建议一类可用于解释新兴行为的转换，并提出了有效搜索解释的方法。我们演示了一组标准基准测试的方法。