深度神经网络的可解释性已成为勘探的主要领域。虽然这些网络在许多任务中实现了最先进的准确性，但极难解释和解释他们的决定。在这项工作中，我们分析了深度卷积网络的最终和倒数第二层，并提供了一种有效的方法，用于识别贡献对网络决定的最大贡献的特征子集。我们证明，与最终层的尺寸相比，每个类的这种特征的数量远低得多，因此深CNN的决定表面位于低维歧管上，并且与网络深度成比例。我们的方法允许将最终层分解为单独的子空间，该子空间远远不可解释，并且与完整网络的最终层相比具有较低的计算成本。

We propose an ensemble approach to predict the labels in linear programming word problems. The entity identification and the meaning representation are two types of tasks to be solved in the NL4Opt competition. We propose the ensembleCRF method to identify the named entities for the first task. We found that single models didn't improve for the given task in our analysis. A set of prediction models predict the entities. The generated results are combined to form a consensus result in the ensembleCRF method. We present an ensemble text generator to produce the representation sentences for the second task. We thought of dividing the problem into multiple small tasks due to the overflow in the output. A single model generates different representations based on the prompt. All the generated text is combined to form an ensemble and produce a mathematical meaning of a linear programming problem.

This paper presents a safety-critical locomotion control framework for quadrupedal robots. Our goal is to enable quadrupedal robots to safely navigate in cluttered environments. To tackle this, we introduce exponential Discrete Control Barrier Functions (exponential DCBFs) with duality-based obstacle avoidance constraints into a Nonlinear Model Predictive Control (NMPC) with Whole-Body Control (WBC) framework for quadrupedal locomotion control. This enables us to use polytopes to describe the shapes of the robot and obstacles for collision avoidance while doing locomotion control of quadrupedal robots. Compared to most prior work, especially using CBFs, that utilize spherical and conservative approximation for obstacle avoidance, this work demonstrates a quadrupedal robot autonomously and safely navigating through very tight spaces in the real world. (Our open-source code is available at github.com/HybridRobotics/quadruped_nmpc_dcbf_duality, and the video is available at youtu.be/p1gSQjwXm1Q.)

Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large version, and investigate how faithful their representations are with respect to the semantic content of texts. We formalize a notion of semantic faithfulness, in which the semantic content of a text should causally figure in a model's inferences in question answering. We then test this notion by observing a model's behavior on answering questions about a story after performing two novel semantic interventions -- deletion intervention and negation intervention. While transformer models achieve high performance on standard question answering tasks, we show that they fail to be semantically faithful once we perform these interventions for a significant number of cases (~50% for deletion intervention, and ~20% drop in accuracy for negation intervention). We then propose an intervention-based training regime that can mitigate the undesirable effects for deletion intervention by a significant margin (from ~50% to ~6%). We analyze the inner-workings of the models to better understand the effectiveness of intervention-based training for deletion intervention. But we show that this training does not attenuate other aspects of semantic unfaithfulness such as the models' inability to deal with negation intervention or to capture the predicate-argument structure of texts. We also test InstructGPT, via prompting, for its ability to handle the two interventions and to capture predicate-argument structure. While InstructGPT models do achieve very high performance on predicate-argument structure task, they fail to respond adequately to our deletion and negation interventions.

Deep Neural Networks (DNN) are becoming increasingly more important in assisted and automated driving. Using such entities which are obtained using machine learning is inevitable: tasks such as recognizing traffic signs cannot be developed reasonably using traditional software development methods. DNN however do have the problem that they are mostly black boxes and therefore hard to understand and debug. One particular problem is that they are prone to hidden backdoors. This means that the DNN misclassifies its input, because it considers properties that should not be decisive for the output. Backdoors may either be introduced by malicious attackers or by inappropriate training. In any case, detecting and removing them is important in the automotive area, as they might lead to safety violations with potentially severe consequences. In this paper, we introduce a novel method to remove backdoors. Our method works for both intentional as well as unintentional backdoors. We also do not require prior knowledge about the shape or distribution of backdoors. Experimental evidence shows that our method performs well on several medium-sized examples.

Multi-Exit models (MEMs) use an early-exit strategy to improve the accuracy and efficiency of deep neural networks (DNNs) by allowing samples to exit the network before the last layer. However, the effectiveness of MEMs in the presence of distribution shifts remains largely unexplored. Our work examines how distribution shifts generated by common image corruptions affect the accuracy/efficiency of MEMs. We find that under common corruptions, early-exiting at the first correct exit reduces the inference cost and provides a significant boost in accuracy ( 10%) over exiting at the last layer. However, with realistic early-exit strategies, which do not assume knowledge about the correct exits, MEMs still reduce inference cost but provide a marginal improvement in accuracy (1%) compared to exiting at the last layer. Moreover, the presence of distribution shift widens the gap between an MEM's maximum classification accuracy and realistic early-exit strategies by 5% on average compared with the gap on in-distribution data. Our empirical analysis shows that the lack of calibration due to a distribution shift increases the susceptibility of such early-exit strategies to exit early and increases misclassification rates. Furthermore, the lack of calibration increases the inconsistency in the predictions of the model across exits, leading to both inefficient inference and more misclassifications compared with evaluation on in-distribution data. Finally, we propose two metrics, underthinking and overthinking, that quantify the different behavior of practical early-exit strategy under distribution shifts, and provide insights into improving the practical utility of MEMs.

Reinforcement learning (RL) operating on attack graphs leveraging cyber terrain principles are used to develop reward and state associated with determination of surveillance detection routes (SDR). This work extends previous efforts on developing RL methods for path analysis within enterprise networks. This work focuses on building SDR where the routes focus on exploring the network services while trying to evade risk. RL is utilized to support the development of these routes by building a reward mechanism that would help in realization of these paths. The RL algorithm is modified to have a novel warm-up phase which decides in the initial exploration which areas of the network are safe to explore based on the rewards and penalty scale factor.

Real engineering and scientific applications often involve one or more qualitative inputs. Standard Gaussian processes (GPs), however, cannot directly accommodate qualitative inputs. The recently introduced latent variable Gaussian process (LVGP) overcomes this issue by first mapping each qualitative factor to underlying latent variables (LVs), and then uses any standard GP covariance function over these LVs. The LVs are estimated similarly to the other GP hyperparameters through maximum likelihood estimation, and then plugged into the prediction expressions. However, this plug-in approach will not account for uncertainty in estimation of the LVs, which can be significant especially with limited training data. In this work, we develop a fully Bayesian approach for the LVGP model and for visualizing the effects of the qualitative inputs via their LVs. We also develop approximations for scaling up LVGPs and fully Bayesian inference for the LVGP hyperparameters. We conduct numerical studies comparing plug-in inference against fully Bayesian inference over a few engineering models and material design applications. In contrast to previous studies on standard GP modeling that have largely concluded that a fully Bayesian treatment offers limited improvements, our results show that for LVGP modeling it offers significant improvements in prediction accuracy and uncertainty quantification over the plug-in approach.

水下机器人通常依靠声纳等声传感器来感知周围的环境。但是，这些传感器通常被多种源和噪声类型淹没，这使得使用原始数据对特征，对象或边界返回的任何有意义的推断都非常困难。尽管存在几种传统的处理噪声方法，但它们的成功率并不令人满意。本文介绍了有条件生成的对抗网络（CGAN）的新应用，以训练模型以产生无噪声的声纳图像，从而优于几种常规过滤方法。估计自由空间对于执行主动探索和映射的自主机器人至关重要。因此，与常规方法相比，我们将方法应用于水下占用映射的任务，并显示出卓越的自由和占用空间推断。

预计在现实世界中部署的NLU系统将定期更新或对随着时间的推移积累的新培训示例的基础神经网络进行重新更新。在我们的工作中，我们专注于多语言环境，在该环境中，我们希望在该设置中进一步捕获有关上述模型已经接受过培训的NLU任务的新培训数据的多语言模型。我们表明，在某些条件下，天真地更新多语言模型可能会导致语言子集的性能损失，尽管汇总性能指标显示出改进。我们在属于三个任务系列（令牌级，句子级别和SEQ2SEQ）的四个任务上建立了这种现象，并发现基线远非手头设置的理想选择。然后，我们基于最近进步的参数有效填充，以开发新颖的填充管道，使我们能够共同最大程度地减少灾难性的遗忘，同时鼓励积极的跨语言转移，从而改善不同语言的增长，同时减少这种设置中损失的损失。