最近的作品证明了过度参数化学习中的双重下降现象：随着模型参数的数量的增加，多余的风险具有$ \ mathsf {u} $ - 在开始时形状，然后在模型高度过度参数化时再次减少。尽管最近在不同的环境（例如线性模型，随机特征模型和内核方法）下进行了研究，但在理论上尚未完全理解这种现象。在本文中，我们考虑了由两种随机特征组成的双随机特征模型（DRFM），并研究DRFM在脊回归中实现的多余风险。我们计算高维框架下的多余风险的确切限制，在这种框架上，训练样本量，数据尺寸和随机特征的维度往往会成比例地无限。根据计算，我们证明DRFM的风险曲线可以表现出三重下降。然后，我们提供三重下降现象的解释，并讨论随机特征维度，正则化参数和信噪比比率如何控制DRFMS风险曲线的形状。最后，我们将研究扩展到多个随机功能模型（MRFM），并表明具有$ K $类型的随机功能的MRFM可能会显示出$（K+1）$ - 折叠。我们的分析指出，具有特定数量下降的风险曲线通常在基于特征的回归中存在。另一个有趣的发现是，当学习神经网络在“神经切线内核”制度中时，我们的结果可以恢复文献中报告的风险峰值位置。

致力于解释深度学习的成功。随机矩阵理论（RMT）为此提供了一种新的方式：涉及训练的深神经网络（DNN）中涉及的大型随机矩阵的光谱分析，例如重量矩阵或HESSIAN矩阵相对于随机梯度下降算法。在本文中，我们对不同模块中的重量矩阵进行了广泛的实验，例如层，网络和数据集，分析其光谱的演变。我们发现这些光谱可以分为三种主要类型：MAR \ V {C} ENKO-BIRCUR频谱（MP），MAR \ V {C} ENKO-BIREUR光谱，具有少量出血异常值（MPB）和重型尾光谱（ H T）。此外，这些发现的光谱直接连接到DNN中的正则化程度。我们认为正规化程度取决于提供给DNN的数据的质量，即数据驱动正规化。这些发现在几个NNS中验证，使用高斯合成数据和真实数据集（MNIST和CIFAR10）。最后，我们提出了一种光谱标准，并且当使用光谱类型与正则化程度之间的连接而没有测试数据时，在没有测试数据的情况下，在没有测试数据的情况下，建立早期停止过程。这种早期停止的DNN避免了不必要的额外培训，同时保持了许多可比的概括能力。

Despite significant progress in object categorization, in recent years, a number of important challenges remain; mainly, the ability to learn from limited labeled data and to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it has only been shown to work with limited sized class vocabularies and typically requires separation between supervised and unsupervised classes, allowing former to inform the latter but not vice versa. We propose the notion of vocabulary-informed learning to alleviate the above mentioned challenges and address problems of supervised, zero-shot, generalized zero-shot and open set recognition using a unified framework. Specifically, we propose a weighted maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms. Distance constraints ensure that labeled samples are projected closer to their correct prototypes, in the embedding space, than to others. We illustrate that resulting model shows improvements in supervised, zero-shot, generalized zero-shot, and large open set recognition, with up to 310K class vocabulary on Animal with Attributes and ImageNet datasets.

Deploying reliable deep learning techniques in interdisciplinary applications needs learned models to output accurate and ({even more importantly}) explainable predictions. Existing approaches typically explicate network outputs in a post-hoc fashion, under an implicit assumption that faithful explanations come from accurate predictions/classifications. We have an opposite claim that explanations boost (or even determine) classification. That is, end-to-end learning of explanation factors to augment discriminative representation extraction could be a more intuitive strategy to inversely assure fine-grained explainability, e.g., in those neuroimaging and neuroscience studies with high-dimensional data containing noisy, redundant, and task-irrelevant information. In this paper, we propose such an explainable geometric deep network dubbed as NeuroExplainer, with applications to uncover altered infant cortical development patterns associated with preterm birth. Given fundamental cortical attributes as network input, our NeuroExplainer adopts a hierarchical attention-decoding framework to learn fine-grained attentions and respective discriminative representations to accurately recognize preterm infants from term-born infants at term-equivalent age. NeuroExplainer learns the hierarchical attention-decoding modules under subject-level weak supervision coupled with targeted regularizers deduced from domain knowledge regarding brain development. These prior-guided constraints implicitly maximizes the explainability metrics (i.e., fidelity, sparsity, and stability) in network training, driving the learned network to output detailed explanations and accurate classifications. Experimental results on the public dHCP benchmark suggest that NeuroExplainer led to quantitatively reliable explanation results that are qualitatively consistent with representative neuroimaging studies.

Medical image segmentation (MIS) is essential for supporting disease diagnosis and treatment effect assessment. Despite considerable advances in artificial intelligence (AI) for MIS, clinicians remain skeptical of its utility, maintaining low confidence in such black box systems, with this problem being exacerbated by low generalization for out-of-distribution (OOD) data. To move towards effective clinical utilization, we propose a foundation model named EvidenceCap, which makes the box transparent in a quantifiable way by uncertainty estimation. EvidenceCap not only makes AI visible in regions of uncertainty and OOD data, but also enhances the reliability, robustness, and computational efficiency of MIS. Uncertainty is modeled explicitly through subjective logic theory to gather strong evidence from features. We show the effectiveness of EvidenceCap in three segmentation datasets and apply it to the clinic. Our work sheds light on clinical safe applications and explainable AI, and can contribute towards trustworthiness in the medical domain.

While inferring common actor states (such as position or velocity) is an important and well-explored task of the perception system aboard a self-driving vehicle (SDV), it may not always provide sufficient information to the SDV. This is especially true in the case of active emergency vehicles (EVs), where light-based signals also need to be captured to provide a full context. We consider this problem and propose a sequential methodology for the detection of active EVs, using an off-the-shelf CNN model operating at a frame level and a downstream smoother that accounts for the temporal aspect of flashing EV lights. We also explore model improvements through data augmentation and training with additional hard samples.

Seismic data often undergoes severe noise due to environmental factors, which seriously affects subsequent applications. Traditional hand-crafted denoisers such as filters and regularizations utilize interpretable domain knowledge to design generalizable denoising techniques, while their representation capacities may be inferior to deep learning denoisers, which can learn complex and representative denoising mappings from abundant training pairs. However, due to the scarcity of high-quality training pairs, deep learning denoisers may sustain some generalization issues over various scenarios. In this work, we propose a self-supervised method that combines the capacities of deep denoiser and the generalization abilities of hand-crafted regularization for seismic data random noise attenuation. Specifically, we leverage the Self2Self (S2S) learning framework with a trace-wise masking strategy for seismic data denoising by solely using the observed noisy data. Parallelly, we suggest the weighted total variation (WTV) to further capture the horizontal local smooth structure of seismic data. Our method, dubbed as S2S-WTV, enjoys both high representation abilities brought from the self-supervised deep network and good generalization abilities of the hand-crafted WTV regularizer and the self-supervised nature. Therefore, our method can more effectively and stably remove the random noise and preserve the details and edges of the clean signal. To tackle the S2S-WTV optimization model, we introduce an alternating direction multiplier method (ADMM)-based algorithm. Extensive experiments on synthetic and field noisy seismic data demonstrate the effectiveness of our method as compared with state-of-the-art traditional and deep learning-based seismic data denoising methods.

With the development of natural language processing techniques(NLP), automatic diagnosis of eye diseases using ophthalmology electronic medical records (OEMR) has become possible. It aims to evaluate the condition of both eyes of a patient respectively, and we formulate it as a particular multi-label classification task in this paper. Although there are a few related studies in other diseases, automatic diagnosis of eye diseases exhibits unique characteristics. First, descriptions of both eyes are mixed up in OEMR documents, with both free text and templated asymptomatic descriptions, resulting in sparsity and clutter of information. Second, OEMR documents contain multiple parts of descriptions and have long document lengths. Third, it is critical to provide explainability to the disease diagnosis model. To overcome those challenges, we present an effective automatic eye disease diagnosis framework, NEEDED. In this framework, a preprocessing module is integrated to improve the density and quality of information. Then, we design a hierarchical transformer structure for learning the contextualized representations of each sentence in the OEMR document. For the diagnosis part, we propose an attention-based predictor that enables traceable diagnosis by obtaining disease-specific information. Experiments on the real dataset and comparison with several baseline models show the advantage and explainability of our framework.

Feature transformation for AI is an essential task to boost the effectiveness and interpretability of machine learning (ML). Feature transformation aims to transform original data to identify an optimal feature space that enhances the performances of a downstream ML model. Existing studies either combines preprocessing, feature selection, and generation skills to empirically transform data, or automate feature transformation by machine intelligence, such as reinforcement learning. However, existing studies suffer from: 1) high-dimensional non-discriminative feature space; 2) inability to represent complex situational states; 3) inefficiency in integrating local and global feature information. To fill the research gap, we formulate the feature transformation task as an iterative, nested process of feature generation and selection, where feature generation is to generate and add new features based on original features, and feature selection is to remove redundant features to control the size of feature space. Finally, we present extensive experiments and case studies to illustrate 24.7\% improvements in F1 scores compared with SOTAs and robustness in high-dimensional data.

During X-ray computed tomography (CT) scanning, metallic implants carrying with patients often lead to adverse artifacts in the captured CT images and then impair the clinical treatment. Against this metal artifact reduction (MAR) task, the existing deep-learning-based methods have gained promising reconstruction performance. Nevertheless, there is still some room for further improvement of MAR performance and generalization ability, since some important prior knowledge underlying this specific task has not been fully exploited. Hereby, in this paper, we carefully analyze the characteristics of metal artifacts and propose an orientation-shared convolution representation strategy to adapt the physical prior structures of artifacts, i.e., rotationally symmetrical streaking patterns. The proposed method rationally adopts Fourier-series-expansion-based filter parametrization in artifact modeling, which can better separate artifacts from anatomical tissues and boost the model generalizability. Comprehensive experiments executed on synthesized and clinical datasets show the superiority of our method in detail preservation beyond the current representative MAR methods. Code will be available at \url{https://github.com/hongwang01/OSCNet}