无示例性课程学习（CIL）是一个具有挑战性的问题，因为严格禁止从先前阶段进行排练数据，从而导致灾难性忘记深度神经网络（DNNS）。在本文中，我们提出了ivoro，这是CIL的整体框架，源自计算几何形状。我们发现Voronoi图（VD）是一个用于空间细分的经典模型，对于解决CIL问题特别有力，因为VD本身可以以增量的方式构建好 - 新添加的站点（类）只会影响接近的类别，使非连续课程几乎无法忘记。此外，为了找到用于VD构建的更好的中心，我们使用功率图与VD串联DNN，并证明可以通过使用除法和争议算法集成本地DNN模型来优化VD结构。此外，我们的VD结构不限于深度特征空间，而是适用于多个中间特征空间，将VD推广为多中心VD（CIVD），可有效捕获DNN的多元元素特征。重要的是，Ivoro还能够处理不确定性感知的测试时间Voronoi细胞分配，并且在几何不确定性和预测精度之间表现出很高的相关性（高达〜0.9）。与最先进的非exemememplar CIL方法相比，Ivoro将所有内容汇总在一起，分别在CIFAR-100，Tinyimagenet和Imagenet-Subsset上获得了高达25.26％，37.09％和33.21％的改善。总之，Ivoro可以实现高度准确，保护隐私和几何解释的CIL，当禁止使用跨相数据共享时，这特别有用，例如在医疗应用中。我们的代码可在https://machunwei.github.io/ivoro上找到。

光学相干断层扫描（OCT）有助于眼科医生评估黄斑水肿，流体的积累以及微观分辨率的病变。视网膜流体的定量对于OCT引导的治疗管理是必需的，这取决于精确的图像分割步骤。由于对视网膜流体的手动分析是一项耗时，主观和容易出错的任务，因此对快速和健壮的自动解决方案的需求增加了。在这项研究中，提出了一种名为Retifluidnet的新型卷积神经结构，用于多级视网膜流体分割。该模型受益于层次表示使用新的自适应双重注意（SDA）模块的纹理，上下文和边缘特征的学习，多个基于自适应的Skip Connections（SASC）以及一种新颖的多尺度深度自我监督学习（DSL）方案。拟议的SDA模块中的注意机制使该模型能够自动提取不同级别的变形感知表示，并且引入的SASC路径进一步考虑了空间通道相互依存，以串联编码器和解码器单元，从而提高了表示能力。还使用包含加权版本的骰子重叠和基于边缘的连接损失的联合损失函数进行了优化的retifluidnet，其中将多尺度局部损失的几个分层阶段集成到优化过程中。该模型根据三个公开可用数据集进行验证：润饰，Optima和Duke，并与几个基线进行了比较。数据集的实验结果证明了在视网膜OCT分割中提出的模型的有效性，并揭示了建议的方法比现有的最新流体分割算法更有效，以适应各种图像扫描仪器记录的视网膜OCT扫描。

新颖的类发现（NCD）的目的是在一个未标记的数据集中推断出新的类别，该数据集利用了包含不相交但相关类别的标签集的先验知识。现有的研究主要侧重于利用方法学层面的标签集，而不太强调标记集合本身的分析。因此，在本文中，我们从标记的集合中重新考虑了小说类发现，并关注两个核心问题：（i）给定特定的未标记集，什么样的标签集可以最好地支持新颖的类发现？ （ii）NCD的基本前提是标记的集合必须与未标记的集合有关，但是我们如何衡量这种关系？对于（i），我们提出并证实了这样的假设，即NCD可以从具有与未标记集的标签相似性的标签集中受益更多。具体而言，我们通过利用其层次结构结构来建立一个广泛而大规模的基准，在Imagenet上标记/未标记的数据集之间具有不同程度的语义相似性。作为鲜明的对比，现有的NCD基准是根据具有不同类别和图像的标签集开发的，并且完全忽略了语义关系。对于（ii），我们引入了一个数学定义，用于量化标记和未标记集之间的语义相似性。此外，我们使用此指标来确认我们提出的基准测试的有效性，并证明它与NCD性能高度相关。此外，在没有定量分析的情况下，以前的工作通常认为标签信息总是有益的。但是，违反直觉，我们的实验结果表明，使用标签可能会导致低相似性设置中的次级优势。

低功率边缘-AI功能对于支持元视野的设备扩展现实（XR）应用至关重要。在这项工作中，我们研究了两个代表性的XR工作负载：（i）手动检测和（ii）眼睛分割，用于硬件设计空间探索。对于这两种应用，我们都会训练深层神经网络，并分析量化和硬件特定瓶颈的影响。通过模拟，我们评估了CPU和两个收缩推理加速器实现。接下来，我们将这些硬件解决方案与先进的技术节点进行比较。评估了将最新的新兴非易失性记忆技术（STT/SOT/VGSOT MRAM）集成到XR-AI推论管道中的影响。我们发现，可以通过在7nm节点的设计中引入非挥发性记忆来实现手部检测（IPS = 40）和眼部分割（IPS = 6）的显着能源益处（IPS = 40）（IPS = 6）。 （推断每秒）。此外，由于MRAM与传统的SRAM相比，由于MRAM的较小形式，我们可以大大减少面积（> = 30％）。

我们表明，在固定级和对称的阳性半明确矩阵上，Riemannian梯度下降算法几乎可以肯定地逃脱了歧管边界上的一些虚假关键点。我们的结果是第一个部分克服低级基质歧管的不完整而不改变香草riemannian梯度下降算法的不完整性。虚假的关键点是一些缺陷的矩阵，仅捕获地面真理的特征成分的一部分。与经典的严格鞍点不同，它们表现出非常奇异的行为。我们表明，使用动力学低级别近似和重新升级的梯度流，可以将某些伪造的临界点转换为参数化域中的经典严格鞍点，从而导致所需的结果。提供数值实验以支持我们的理论发现。

This paper focuses on designing efficient models with low parameters and FLOPs for dense predictions. Even though CNN-based lightweight methods have achieved stunning results after years of research, trading-off model accuracy and constrained resources still need further improvements. This work rethinks the essential unity of efficient Inverted Residual Block in MobileNetv2 and effective Transformer in ViT, inductively abstracting a general concept of Meta-Mobile Block, and we argue that the specific instantiation is very important to model performance though sharing the same framework. Motivated by this phenomenon, we deduce a simple yet efficient modern \textbf{I}nverted \textbf{R}esidual \textbf{M}obile \textbf{B}lock (iRMB) for mobile applications, which absorbs CNN-like efficiency to model short-distance dependency and Transformer-like dynamic modeling capability to learn long-distance interactions. Furthermore, we design a ResNet-like 4-phase \textbf{E}fficient \textbf{MO}del (EMO) based only on a series of iRMBs for dense applications. Massive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, \eg, our EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass \textbf{SoTA} CNN-/Transformer-based models, while trading-off the model accuracy and efficiency well.

Supervised Question Answering systems (QA systems) rely on domain-specific human-labeled data for training. Unsupervised QA systems generate their own question-answer training pairs, typically using secondary knowledge sources to achieve this outcome. Our approach (called PIE-QG) uses Open Information Extraction (OpenIE) to generate synthetic training questions from paraphrased passages and uses the question-answer pairs as training data for a language model for a state-of-the-art QA system based on BERT. Triples in the form of <subject, predicate, object> are extracted from each passage, and questions are formed with subjects (or objects) and predicates while objects (or subjects) are considered as answers. Experimenting on five extractive QA datasets demonstrates that our technique achieves on-par performance with existing state-of-the-art QA systems with the benefit of being trained on an order of magnitude fewer documents and without any recourse to external reference data sources.

Transformer has achieved impressive successes for various computer vision tasks. However, most of existing studies require to pretrain the Transformer backbone on a large-scale labeled dataset (e.g., ImageNet) for achieving satisfactory performance, which is usually unavailable for medical images. Additionally, due to the gap between medical and natural images, the improvement generated by the ImageNet pretrained weights significantly degrades while transferring the weights to medical image processing tasks. In this paper, we propose Bootstrap Own Latent of Transformer (BOLT), a self-supervised learning approach specifically for medical image classification with the Transformer backbone. Our BOLT consists of two networks, namely online and target branches, for self-supervised representation learning. Concretely, the online network is trained to predict the target network representation of the same patch embedding tokens with a different perturbation. To maximally excavate the impact of Transformer from limited medical data, we propose an auxiliary difficulty ranking task. The Transformer is enforced to identify which branch (i.e., online/target) is processing the more difficult perturbed tokens. Overall, the Transformer endeavours itself to distill the transformation-invariant features from the perturbed tokens to simultaneously achieve difficulty measurement and maintain the consistency of self-supervised representations. The proposed BOLT is evaluated on three medical image processing tasks, i.e., skin lesion classification, knee fatigue fracture grading and diabetic retinopathy grading. The experimental results validate the superiority of our BOLT for medical image classification, compared to ImageNet pretrained weights and state-of-the-art self-supervised learning approaches.

Knowledge graph embedding (KGE), which maps entities and relations in a knowledge graph into continuous vector spaces, has achieved great success in predicting missing links in knowledge graphs. However, knowledge graphs often contain incomplete triples that are difficult to inductively infer by KGEs. To address this challenge, we resort to analogical inference and propose a novel and general self-supervised framework AnKGE to enhance KGE models with analogical inference capability. We propose an analogical object retriever that retrieves appropriate analogical objects from entity-level, relation-level, and triple-level. And in AnKGE, we train an analogy function for each level of analogical inference with the original element embedding from a well-trained KGE model as input, which outputs the analogical object embedding. In order to combine inductive inference capability from the original KGE model and analogical inference capability enhanced by AnKGE, we interpolate the analogy score with the base model score and introduce the adaptive weights in the score function for prediction. Through extensive experiments on FB15k-237 and WN18RR datasets, we show that AnKGE achieves competitive results on link prediction task and well performs analogical inference.

Digital engineering transformation is a crucial process for the engineering paradigm shifts in the fourth industrial revolution (4IR), and artificial intelligence (AI) is a critical enabling technology in digital engineering transformation. This article discusses the following research questions: What are the fundamental changes in the 4IR? More specifically, what are the fundamental changes in engineering? What is digital engineering? What are the main uncertainties there? What is trustworthy AI? Why is it important today? What are emerging engineering paradigm shifts in the 4IR? What is the relationship between the data-intensive paradigm and digital engineering transformation? What should we do for digitalization? From investigating the pattern of industrial revolutions, this article argues that ubiquitous machine intelligence (uMI) is the defining power brought by the 4IR. Digitalization is a condition to leverage ubiquitous machine intelligence. Digital engineering transformation towards Industry 4.0 has three essential building blocks: digitalization of engineering, leveraging ubiquitous machine intelligence, and building digital trust and security. The engineering design community at large is facing an excellent opportunity to bring the new capabilities of ubiquitous machine intelligence and trustworthy AI principles, as well as digital trust, together in various engineering systems design to ensure the trustworthiness of systems in Industry 4.0.