最近，致力于通过现代机器学习方法预测脑部疾病的最新神经影像学研究通常包括单一模态并依靠监督的过度参数化模型。但是，单一模态仅提供了高度复杂的大脑的有限视图。至关重要的是，临床环境中的有监督模型缺乏用于培训的准确诊断标签。粗标签不会捕获脑疾病表型的长尾谱，这导致模型的普遍性丧失，从而使它们在诊断环境中的有用程度降低。这项工作提出了一个新型的多尺度协调框架，用于从多模式神经影像数据中学习多个表示。我们提出了一般的归纳偏见分类法，以捕获多模式自学融合中的独特和联合信息。分类法构成了一个无解码器模型的家族，具有降低的计算复杂性，并捕获多模式输入的本地和全局表示之间的多尺度关系。我们使用各种阿尔茨海默氏病表型中使用功能和结构磁共振成像（MRI）数据对分类法进行了全面评估，并表明自我监督模型揭示了与疾病相关的大脑区域和多模态链接，而无需在预先访问PRE-PRE-the PRE-the PRE-the PRE-the PRE-PRECTEN NICKES NOCKER NOCKER NOCKER NOCKER NOCKER NOCE访问。训练。拟议的多模式自学学习的学习能够表现出两种模式的分类表现。伴随的丰富而灵活的无监督的深度学习框架捕获了复杂的多模式关系，并提供了符合或超过更狭窄的监督分类分析的预测性能。我们提供了详尽的定量证据，表明该框架如何显着提高我们对复杂脑部疾病中缺失的联系的搜索。

深度学习已被广​​泛应用于神经影像学，包括预测磁共振成像（MRI）体积的脑表型关系。 MRI数据通常需要进行广泛的预处理，然后才能通过深度学习准备建模，部分原因是其高维和异质性。各种MRI预处理管道都有自己的优势和局限性。最近的研究表明，即使使用相同的数据，与管道相关的变化也可能导致不同的科学发现。同时，机器学习社区强调了从以模型为中心转移到以数据为中心的方法的重要性，因为数据质量在深度学习应用中起着至关重要的作用。在这个想法的激励下，我们首先评估预处理管道选择如何影响监督学习模型的下游表现。接下来，我们提出了两个管道不变表示方法MPSL和PXL，以提高分类性能的一致性并捕获管道对之间的类似神经网络表示。使用来自英国生物库数据集的2000名人类受试者，我们证明了这两种模型都具有独特的优势，特别是可以使用MPSL来改善对新管道的样本概括，而PXL则可以用来提高预测性能一致性和代表性封闭管道集中的相似性。这些结果表明，我们提出的模型可用于克服与管道相关的偏差，并提高神经成像预测任务的可重复性。

是否可以在深网络中重组非线性激活函数以创建硬件有效的模型？为了解决这个问题，我们提出了一个称为重组激活网络（RANS）的新范式，该范式操纵模型中的非线性数量以提高其硬件意识和效率。首先，我们提出了RAN-STHICER（RAN-E） - 一个新的硬件感知搜索空间和半自动搜索算法 - 用硬件感知的块替换效率低下的块。接下来，我们提出了一种称为RAN-IMPLICIC（RAN-I）的无训练模型缩放方法，从理论上讲，我们在非线性单元的数量方面证明了网络拓扑与其表现性之间的联系。我们证明，我们的网络在不同尺度和几种类型的硬件上实现最新的成像网结果。例如，与有效网络-lite-B0相比，RAN-E在ARM Micro-NPU上每秒（FPS）提高了1.5倍，同时提高了类似的精度。另一方面，ran-i以相似或更好的精度表现出#macs的#macs降低2倍。我们还表明，在基于ARM的数据中心CPU上，RAN-I的FPS比Convnext高40％。最后，与基于Convnext的模型相比，基于RAN-I的对象检测网络在数据中心CPU上获得了类似或更高的映射，并且在数据中心CPU上的fps高达33％。

This work investigates unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about locality in the input into the objective can significantly improve a representation's suitability for downstream tasks. We further control characteristics of the representation by matching to a prior distribution adversarially. Our method, which we call Deep InfoMax (DIM), outperforms a number of popular unsupervised learning methods and compares favorably with fully-supervised learning on several classification tasks in with some standard architectures. DIM opens new avenues for unsupervised learning of representations and is an important step towards flexible formulations of representation learning objectives for specific end-goals.

We derive a set of causal deep neural networks whose architectures are a consequence of tensor (multilinear) factor analysis. Forward causal questions are addressed with a neural network architecture composed of causal capsules and a tensor transformer. The former estimate a set of latent variables that represent the causal factors, and the latter governs their interaction. Causal capsules and tensor transformers may be implemented using shallow autoencoders, but for a scalable architecture we employ block algebra and derive a deep neural network composed of a hierarchy of autoencoders. An interleaved kernel hierarchy preprocesses the data resulting in a hierarchy of kernel tensor factor models. Inverse causal questions are addressed with a neural network that implements multilinear projection and estimates the causes of effects. As an alternative to aggressive bottleneck dimension reduction or regularized regression that may camouflage an inherently underdetermined inverse problem, we prescribe modeling different aspects of the mechanism of data formation with piecewise tensor models whose multilinear projections are well-defined and produce multiple candidate solutions. Our forward and inverse neural network architectures are suitable for asynchronous parallel computation.

The existing methods for video anomaly detection mostly utilize videos containing identifiable facial and appearance-based features. The use of videos with identifiable faces raises privacy concerns, especially when used in a hospital or community-based setting. Appearance-based features can also be sensitive to pixel-based noise, straining the anomaly detection methods to model the changes in the background and making it difficult to focus on the actions of humans in the foreground. Structural information in the form of skeletons describing the human motion in the videos is privacy-protecting and can overcome some of the problems posed by appearance-based features. In this paper, we present a survey of privacy-protecting deep learning anomaly detection methods using skeletons extracted from videos. We present a novel taxonomy of algorithms based on the various learning approaches. We conclude that skeleton-based approaches for anomaly detection can be a plausible privacy-protecting alternative for video anomaly detection. Lastly, we identify major open research questions and provide guidelines to address them.

Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations. For real-world applications of RL, recovering underlying latent states is crucial, particularly when sensory inputs contain irrelevant and exogenous information. In this work, we study how information bottlenecks can be used to construct latent states efficiently in the presence of task-irrelevant information. We propose architectures that utilize variational and discrete information bottlenecks, coined as RepDIB, to learn structured factorized representations. Exploiting the expressiveness bought by factorized representations, we introduce a simple, yet effective, bottleneck that can be integrated with any existing self-supervised objective for RL. We demonstrate this across several online and offline RL benchmarks, along with a real robot arm task, where we find that compressed representations with RepDIB can lead to strong performance improvements, as the learned bottlenecks help predict only the relevant state while ignoring irrelevant information.

We propose reconstruction probing, a new analysis method for contextualized representations based on reconstruction probabilities in masked language models (MLMs). This method relies on comparing the reconstruction probabilities of tokens in a given sequence when conditioned on the representation of a single token that has been fully contextualized and when conditioned on only the decontextualized lexical prior of the model. This comparison can be understood as quantifying the contribution of contextualization towards reconstruction -- the difference in the reconstruction probabilities can only be attributed to the representational change of the single token induced by contextualization. We apply this analysis to three MLMs and find that contextualization boosts reconstructability of tokens that are close to the token being reconstructed in terms of linear and syntactic distance. Furthermore, we extend our analysis to finer-grained decomposition of contextualized representations, and we find that these boosts are largely attributable to static and positional embeddings at the input layer.

Diffusion models have achieved justifiable popularity by attaining state-of-the-art performance in generating realistic objects from seemingly arbitrarily complex data distributions, including when conditioning generation on labels. Unfortunately, however, their iterative nature renders them very computationally inefficient during the sampling process. For the multi-class conditional generation problem, we propose a novel, structurally unique framework of diffusion models which are hierarchically branched according to the inherent relationships between classes. In this work, we demonstrate that branched diffusion models offer major improvements in efficiently generating samples from multiple classes. We also showcase several other advantages of branched diffusion models, including ease of extension to novel classes in a continual-learning setting, and a unique interpretability that offers insight into these generative models. Branched diffusion models represent an alternative paradigm to their traditional linear counterparts, and can have large impacts in how we use diffusion models for efficient generation, online learning, and scientific discovery.

The widely studied task of Natural Language Inference (NLI) requires a system to recognize whether one piece of text is textually entailed by another, i.e. whether the entirety of its meaning can be inferred from the other. In current NLI datasets and models, textual entailment relations are typically defined on the sentence- or paragraph-level. However, even a simple sentence often contains multiple propositions, i.e. distinct units of meaning conveyed by the sentence. As these propositions can carry different truth values in the context of a given premise, we argue for the need to recognize the textual entailment relation of each proposition in a sentence individually. We propose PropSegmEnt, a corpus of over 35K propositions annotated by expert human raters. Our dataset structure resembles the tasks of (1) segmenting sentences within a document to the set of propositions, and (2) classifying the entailment relation of each proposition with respect to a different yet topically-aligned document, i.e. documents describing the same event or entity. We establish strong baselines for the segmentation and entailment tasks. Through case studies on summary hallucination detection and document-level NLI, we demonstrate that our conceptual framework is potentially useful for understanding and explaining the compositionality of NLI labels.