神经崩溃的概念是指在各种规范分类问题中经验观察到的几种新兴现象。在训练深度神经网络的终端阶段，同一类的所有示例的特征嵌入往往会崩溃为单一表示，而不同类别的特征往往会尽可能分开。通常通过简化的模型（称为无约束的特征表示）来研究神经崩溃，其中假定模型具有“无限表达性”，并且可以将每个数据点映射到任何任意表示。在这项工作中，我们提出了不受约束的功能表示的更现实的变体，该变体考虑到了网络的有限表达性。经验证据表明，嘈杂数据点的记忆导致神经崩溃的降解（扩张）。使用记忆 - 稀释（M-D）现象的模型，我们展示了一种机制，通过该机制，不同的损失导致嘈杂数据上受过训练的网络的不同性能。我们的证据揭示了为什么标签平滑性（经验观察到产生正则化效果的跨凝性的修改）导致分类任务的概括改善的原因。

消息传递神经网络（MPNN）自从引入卷积神经网络以泛滥到图形结构的数据以来，人们的受欢迎程度急剧上升，现在被认为是解决各种以图形为中心的最先进的工具问题。我们研究图形分类和回归中MPNN的概括误差。我们假设不同类别的图是从不同的随机图模型中采样的。我们表明，当在从这种分布中采样的数据集上训练MPNN时，概括差距会增加MPNN的复杂性，并且不仅相对于训练样本的数量，而且还会减少节点的平均数量在图中。这表明，只要图形很大，具有高复杂性的MPNN如何从图形的小数据集中概括。概括结合是从均匀收敛结果得出的，该结果表明，应用于图的任何MPNN近似于该图离散的几何模型上应用的MPNN。

我们提出了卡通X（卡通解释），这是一种新的模型 - 不可知解释方法，朝向图像分类器定制，并基于速率 - 失真说明（RDE）框架。自然图像大致是典型的平滑信号 - 也称为卡通图像 - 并且在小波域中倾向于稀疏。CartoonX是通过要求其解释在小波域中的稀疏来利用这一点的第一种解释方法，从而提取图像的\ emph {相关的片状平滑}部分而不是相关的像素稀疏区域。我们实际证明了CartoCX由于其片断平稳性，但在解释错误分类时也特别恰当地展示了CardentX。

我们研究光谱图卷积神经网络（GCNN），其中过滤器被定义为通过功能计算的图形移位算子（GSO）的连续函数。光谱GCNN不是针对一个特定图的量身定制的，可以在不同的图之间传输。因此，研究GCNN的可传递性很重要：网络在代表相同现象的不同图上具有大致相同影响的能力。如果测试集中的图与训练集中的图形相同，则可传递性可确保在某些图上进行训练的GCNN概括。在本文中，我们考虑了基于Graphon分析的可转让性模型。图形是图形的极限对象，在图形范式中，如果两者都近似相同的图形，则两个图表示相同的现象。我们的主要贡献可以总结如下：1）我们证明，在近似于同一图形的图的图下，任何具有连续过滤器的固定GCNN都是可以转移的，2）我们证明了近似于未结合的图形换档运算符的图形，该图是在本文中定义的，和3）我们获得了非反应近似结果，证明了GCNN的线性稳定性。这扩展了当前的最新结果，这些结果显示了在近似界图子的图下显示多项式过滤器的渐近可传递性。

全球导航卫星系统通常在城市环境中表现较差，在城市环境中，设备和卫星之间的视线条件的可能性很低，因此需要替代的定位方法才能良好准确。我们提出了Locunet：用于本地化任务的卷积，端到端训练的神经网络，能够从少数基站（BSS）的接收信号强度（RSS）中估算用户的位置。在提出的方法中，要本地化的用户只需将测量的RSS报告给可能位于云中的中央处理单元。使用BSS和RSS测量值的Pathloss无线电图的估计，Locunet可以以最先进的精度定位用户，并在无线电图估计中享有高度鲁棒性。所提出的方法不需要对新环境进行预采样，并且适用于实时应用。此外，提供了两个新颖的数据集，可以在现实的城市环境中对RSS和TOA方法进行数值评估，并为研究社区公开提供。通过使用这些数据集，我们还提供了密集的城市场景中最先进的RSS和基于TOA的方法的公平比较，并以数值显示Locunet优于所有比较方法。

Neural Representations have recently been shown to effectively reconstruct a wide range of signals from 3D meshes and shapes to images and videos. We show that, when adapted correctly, neural representations can be used to directly represent the weights of a pre-trained convolutional neural network, resulting in a Neural Representation for Neural Networks (NeRN). Inspired by coordinate inputs of previous neural representation methods, we assign a coordinate to each convolutional kernel in our network based on its position in the architecture, and optimize a predictor network to map coordinates to their corresponding weights. Similarly to the spatial smoothness of visual scenes, we show that incorporating a smoothness constraint over the original network's weights aids NeRN towards a better reconstruction. In addition, since slight perturbations in pre-trained model weights can result in a considerable accuracy loss, we employ techniques from the field of knowledge distillation to stabilize the learning process. We demonstrate the effectiveness of NeRN in reconstructing widely used architectures on CIFAR-10, CIFAR-100, and ImageNet. Finally, we present two applications using NeRN, demonstrating the capabilities of the learned representations.

A core process in human cognition is analogical mapping: the ability to identify a similar relational structure between different situations. We introduce a novel task, Visual Analogies of Situation Recognition, adapting the classical word-analogy task into the visual domain. Given a triplet of images, the task is to select an image candidate B' that completes the analogy (A to A' is like B to what?). Unlike previous work on visual analogy that focused on simple image transformations, we tackle complex analogies requiring understanding of scenes. We leverage situation recognition annotations and the CLIP model to generate a large set of 500k candidate analogies. Crowdsourced annotations for a sample of the data indicate that humans agree with the dataset label ~80% of the time (chance level 25%). Furthermore, we use human annotations to create a gold-standard dataset of 3,820 validated analogies. Our experiments demonstrate that state-of-the-art models do well when distractors are chosen randomly (~86%), but struggle with carefully chosen distractors (~53%, compared to 90% human accuracy). We hope our dataset will encourage the development of new analogy-making models. Website: https://vasr-dataset.github.io/

Micron-scale robots (ubots) have recently shown great promise for emerging medical applications, and accurate control of ubots is a critical next step to deploying them in real systems. In this work, we develop the idea of a nonlinear mismatch controller to compensate for the mismatch between the disturbed unicycle model of a rolling ubot and trajectory data collected during an experiment. We exploit the differential flatness property of the rolling ubot model to generate a mapping from the desired state trajectory to nominal control actions. Due to model mismatch and parameter estimation error, the nominal control actions will not exactly reproduce the desired state trajectory. We employ a Gaussian Process (GP) to learn the model mismatch as a function of the desired control actions, and correct the nominal control actions using a least-squares optimization. We demonstrate the performance of our online learning algorithm in simulation, where we show that the model mismatch makes some desired states unreachable. Finally, we validate our approach in an experiment and show that the error metrics are reduced by up to 40%.

A master face is a face image that passes face-based identity authentication for a high percentage of the population. These faces can be used to impersonate, with a high probability of success, any user, without having access to any user information. We optimize these faces for 2D and 3D face verification models, by using an evolutionary algorithm in the latent embedding space of the StyleGAN face generator. For 2D face verification, multiple evolutionary strategies are compared, and we propose a novel approach that employs a neural network to direct the search toward promising samples, without adding fitness evaluations. The results we present demonstrate that it is possible to obtain a considerable coverage of the identities in the LFW or RFW datasets with less than 10 master faces, for six leading deep face recognition systems. In 3D, we generate faces using the 2D StyleGAN2 generator and predict a 3D structure using a deep 3D face reconstruction network. When employing two different 3D face recognition systems, we are able to obtain a coverage of 40%-50%. Additionally, we present the generation of paired 2D RGB and 3D master faces, which simultaneously match 2D and 3D models with high impersonation rates.

The use of needles to access sites within organs is fundamental to many interventional medical procedures both for diagnosis and treatment. Safe and accurate navigation of a needle through living tissue to an intra-tissue target is currently often challenging or infeasible due to the presence of anatomical obstacles in the tissue, high levels of uncertainty, and natural tissue motion (e.g., due to breathing). Medical robots capable of automating needle-based procedures in vivo have the potential to overcome these challenges and enable an enhanced level of patient care and safety. In this paper, we show the first medical robot that autonomously navigates a needle inside living tissue around anatomical obstacles to an intra-tissue target. Our system leverages an aiming device and a laser-patterned highly flexible steerable needle, a type of needle capable of maneuvering along curvilinear trajectories to avoid obstacles. The autonomous robot accounts for anatomical obstacles and uncertainty in living tissue/needle interaction with replanning and control and accounts for respiratory motion by defining safe insertion time windows during the breathing cycle. We apply the system to lung biopsy, which is critical in the diagnosis of lung cancer, the leading cause of cancer-related death in the United States. We demonstrate successful performance of our system in multiple in vivo porcine studies and also demonstrate that our approach leveraging autonomous needle steering outperforms a standard manual clinical technique for lung nodule access.