受生物学最复杂的计算机的启发，大脑，神经网络构成了计算原理的深刻重新重新制定。值得注意的是，在活细胞内部的信息处理分子系统（例如信号转导级联和遗传调节网络）内，在信息处理的分子系统中也出现了类似的高维，高度相关的计算体系结构。在其他物理和化学过程中，即使表面上扮演非信息处理的角色，例如蛋白质合成，代谢或结构自组装等表面上，神经形态集体模式是否会更广泛地发现。在这里，我们检查了多组分结构自组装过程中的成核，表明可以以类似于神经网络计算的方式对高维浓度模式进行区分和分类。具体而言，我们设计了一组917个DNA瓷砖，可以以三种替代方式自组装，从而使竞争成核敏感地取决于三个结构中高分化瓷砖共定位的程度。该系统经过训练，以将18个灰度30 x 30像素图像分为三类。在150小时的退火过程中和之后，在实验上，荧光和原子力显微镜监测确定所有训练有素的图像均正确分类，而一组图像变化集探测了结果的鲁棒性。尽管与先前的生化神经网络相比缓慢，但我们的方法令人惊讶地紧凑，健壮且可扩展。这种成功表明，无处不在的物理现象（例如成核）在将高维多分量系统缩放时可能具有强大的信息处理能力。

IoT sensors, especially video cameras, are ubiquitously deployed around the world to perform a variety of computer vision tasks in several verticals including retail, healthcare, safety and security, transportation, manufacturing, etc. To amortize their high deployment effort and cost, it is desirable to perform multiple video analytics tasks, which we refer to as Analytical Units (AUs), off the video feed coming out of every camera. In this paper, we first show that in a multi-AU setting, changing the camera setting has disproportionate impact on different AUs performance. In particular, the optimal setting for one AU may severely degrade the performance for another AU, and further the impact on different AUs varies as the environmental condition changes. We then present Elixir, a system to enhance the video stream quality for multiple analytics on a video stream. Elixir leverages Multi-Objective Reinforcement Learning (MORL), where the RL agent caters to the objectives from different AUs and adjusts the camera setting to simultaneously enhance the performance of all AUs. To define the multiple objectives in MORL, we develop new AU-specific quality estimator values for each individual AU. We evaluate Elixir through real-world experiments on a testbed with three cameras deployed next to each other (overlooking a large enterprise parking lot) running Elixir and two baseline approaches, respectively. Elixir correctly detects 7.1% (22,068) and 5.0% (15,731) more cars, 94% (551) and 72% (478) more faces, and 670.4% (4975) and 158.6% (3507) more persons than the default-setting and time-sharing approaches, respectively. It also detects 115 license plates, far more than the time-sharing approach (7) and the default setting (0).

Advancement in large pretrained language models has significantly improved their performance for conditional language generation tasks including summarization albeit with hallucinations. To reduce hallucinations, conventional methods proposed improving beam search or using a fact checker as a postprocessing step. In this paper, we investigate the use of the Natural Language Inference (NLI) entailment metric to detect and prevent hallucinations in summary generation. We propose an NLI-assisted beam re-ranking mechanism by computing entailment probability scores between the input context and summarization model-generated beams during saliency-enhanced greedy decoding. Moreover, a diversity metric is introduced to compare its effectiveness against vanilla beam search. Our proposed algorithm significantly outperforms vanilla beam decoding on XSum and CNN/DM datasets.

Generative Adversarial Networks (GANs) have received wide acclaim among the machine learning (ML) community for their ability to generate realistic 2D images. ML is being applied more often to complex problems beyond those of computer vision. However, current frameworks often serve as black boxes and lack physics embeddings, leading to poor ability in enforcing constraints and unreliable models. In this work, we develop physics embeddings that can be stringently imposed, referred to as hard constraints, in the neural network architecture. We demonstrate their capability for 3D turbulence by embedding them in GANs, particularly to enforce the mass conservation constraint in incompressible fluid turbulence. In doing so, we also explore and contrast the effects of other methods of imposing physics constraints within the GANs framework, especially penalty-based physics constraints popular in literature. By using physics-informed diagnostics and statistics, we evaluate the strengths and weaknesses of our approach and demonstrate its feasibility.

Structural alterations have been thoroughly investigated in the brain during the early onset of schizophrenia (SCZ) with the development of neuroimaging methods. The objective of the paper is an efficient classification of SCZ in 2 different classes: Cognitive Normal (CN), and SCZ using magnetic resonance imaging (MRI) images. This paper proposed a lightweight 3D convolutional neural network (CNN) based framework for SCZ diagnosis using MRI images. In the proposed model, lightweight 3D CNN is used to extract both spatial and spectral features simultaneously from 3D volume MRI scans, and classification is done using an ensemble bagging classifier. Ensemble bagging classifier contributes to preventing overfitting, reduces variance, and improves the model's accuracy. The proposed algorithm is tested on datasets taken from three benchmark databases available as open-source: MCICShare, COBRE, and fBRINPhase-II. These datasets have undergone preprocessing steps to register all the MRI images to the standard template and reduce the artifacts. The model achieves the highest accuracy 92.22%, sensitivity 94.44%, specificity 90%, precision 90.43%, recall 94.44%, F1-score 92.39% and G-mean 92.19% as compared to the current state-of-the-art techniques. The performance metrics evidenced the use of this model to assist the clinicians for automatic accurate diagnosis of SCZ.

The process of screening molecules for desirable properties is a key step in several applications, ranging from drug discovery to material design. During the process of drug discovery specifically, protein-ligand docking, or chemical docking, is a standard in-silico scoring technique that estimates the binding affinity of molecules with a specific protein target. Recently, however, as the number of virtual molecules available to test has rapidly grown, these classical docking algorithms have created a significant computational bottleneck. We address this problem by introducing Deep Surrogate Docking (DSD), a framework that applies deep learning-based surrogate modeling to accelerate the docking process substantially. DSD can be interpreted as a formalism of several earlier surrogate prefiltering techniques, adding novel metrics and practical training practices. Specifically, we show that graph neural networks (GNNs) can serve as fast and accurate estimators of classical docking algorithms. Additionally, we introduce FiLMv2, a novel GNN architecture which we show outperforms existing state-of-the-art GNN architectures, attaining more accurate and stable performance by allowing the model to filter out irrelevant information from data more efficiently. Through extensive experimentation and analysis, we show that the DSD workflow combined with the FiLMv2 architecture provides a 9.496x speedup in molecule screening with a <3% recall error rate on an example docking task. Our open-source code is available at https://github.com/ryienh/graph-dock.

Dynamic movement primitives are widely used for learning skills which can be demonstrated to a robot by a skilled human or controller. While their generalization capabilities and simple formulation make them very appealing to use, they possess no strong guarantees to satisfy operational safety constraints for a task. In this paper, we present constrained dynamic movement primitives (CDMP) which can allow for constraint satisfaction in the robot workspace. We present a formulation of a non-linear optimization to perturb the DMP forcing weights regressed by locally-weighted regression to admit a Zeroing Barrier Function (ZBF), which certifies workspace constraint satisfaction. We demonstrate the proposed CDMP under different constraints on the end-effector movement such as obstacle avoidance and workspace constraints on a physical robot. A video showing the implementation of the proposed algorithm using different manipulators in different environments could be found here https://youtu.be/hJegJJkJfys.

将视频视为一系列图像（框架），并重新使用Deep Neur网络模型，这是一种常见的做法，这些模型仅在视频上的图像上接受图像进行培训。在本文中，我们表明，这种信念的飞跃是，在图像上运作良好的深度学习模型也将在视频上效果很好。我们表明，即使摄像机正在查看没有以任何可察觉的方式变化的场景，并且我们控制了视频压缩和环境（照明）等外部因素，视频分析应用程序的准确性也会显着波动。发生这些波动是因为摄像机产生的连续帧可能在视觉上看起来相似，但是视频分析应用程序对这些帧的看法却大不相同。我们观察到这些波动的根本原因是摄像机自动进行的动态摄像头参数更改，以捕获和生成视觉上令人愉悦的视频。摄像机无意间充当无意的对手，因为如我们所示，连续帧中图像像素值的这些微小变化对从视频分析任务中重新使用图像训练的深度学习模型的见解的准确性产生了显着不利影响。为了从相机中解决这种无意的对抗效应，我们探讨了转移学习技术通过从图像分析任务中学习的知识转移来改善视频分析任务中的学习。特别是，我们表明，我们新训练的Yolov5模型在跨帧的对象检测中减少了波动，从而可以更好地跟踪对象（跟踪中的错误少40％）。我们的论文还提供了新的方向和技术，以减轻相机对用于视频分析应用程序的深度学习模型的对抗性影响。

Duckiebots是低成本的移动机器人，在研究和教育领域广泛使用。尽管Duckietown平台有现有的自动驾驶算法，但它们要么太复杂，要么表现太差，无法导航多车道轨道。此外，必须将内存和计算资源提供给Duckiebot，以便它可以执行其他任务，例如分布式输入检测。为了满足这些约束，我们构建了一种低成本的自主驾驶算法，能够在两车道轨道上驾驶。该算法使用传统的计算机视觉技术来识别轨道上的中央车道并获得相关的转向角度。然后，转向由PID控制器控制，该PID控制器使Duckiebot的运动平滑。将算法的性能与Neurips 2018 AI驾驶奥运会（AIDO）决赛入围者进行了比较，并且除了一名决赛选手以外，它的表现优于所有球员。我们算法的两个主要贡献是其低计算要求和非常快速的设置，并持续努力使其更加可靠。

仇恨言论以贬义的评论以多种形式针对社区，并使人类退后一步。 Hatexplain是最近出版的第一个数据集，用于以理由的形式使用带注释的跨度，以及语音分类类别和有针对性的社区，以使分类更具人性化，可解释，准确和偏见。我们调整BERT以理由和阶级预测的形式执行此任务，并比较我们对跨精度，解释性和偏见的不同指标的性能。我们的新颖性是三倍。首先，我们尝试具有不同重要性值的合并理由类损失。其次，我们对理由的地面真相注意值进行了广泛的实验。随着保守和宽大的关注，我们比较了hatexplain模型的性能并检验我们的假设。第三，为了改善模型中的意外偏见，我们使用目标社区单词的掩盖，并注意偏见和解释性指标的改善。总体而言，我们成功地实现了模型的解释性，偏差删除和对原始BERT实施的几个增量改进。