Search

This work addresses the challenge of capturing the complexities of legal knowledge by proposing a multi-layered embedding-based retrieval method for legal and legislative texts. Creating embeddings not only for individual articles but also for their components (paragraphs, clauses) and structural groupings (books, titles, chapters, etc), we seek to capture the subtleties of legal information through the use of dense vectors of embeddings, representing it at varying levels of granularity. Our method meets various information needs by allowing the Retrieval Augmented Generation system to provide accurate responses, whether for specific segments or entire sections, tailored to the user's query. We explore the concepts of aboutness, semantic chunking, and inherent hierarchy within legal texts, arguing that this method enhances the legal information retrieval. Despite the focus being on Brazil's legislative methods and the Brazilian Constitution, which follow a civil law tradition, our findings should in principle be applicable across different legal systems, including those adhering to common law traditions. Furthermore, the principles of the proposed method extend beyond the legal domain, offering valuable insights for organizing and retrieving information in any field characterized by information encoded in hierarchical text., Comment: 27 pages, 10 figures

Big data processing has exposed the limits of compute-centric hardware acceleration due to the memory-to-processor bandwidth bottleneck. Consequently, there has been a shift towards memory-centric architectures, leveraging substantial compute parallelism by processing using the memory elements directly. Computing-in-memory (CIM) proposals for both conventional and emerging memory technologies often target massively parallel operations. However, current CIM solutions face significant challenges. For emerging data-intensive applications, such as advanced machine learning techniques and bioinformatics, where matrix multiplication is a key primitive, memristor crossbars suffer from limited write endurance and expensive write operations. In contrast, while DRAM-based solutions have successfully demonstrated multiplication using additions, they remain prohibitively slow. This paper introduces Count2Multiply, a technology-agnostic digital-CIM method for performing integer-binary and integer-integer matrix multiplications using high-radix, massively parallel counting implemented with bitwise logic operations. In addition, Count2Multiply is designed with fault tolerance in mind and leverages traditional scalable row-wise error correction codes, such as Hamming and BCH codes, to protect against the high error rates of existing CIM designs. We demonstrate Count2Multiply with a detailed application to CIM in conventional DRAM due to its ubiquity and high endurance. We also explore the acceleration potential of racetrack memories due to their shifting properties, which are natural for Count2Multiply, and their high endurance. Compared to the state-of-the-art in-DRAM method, Count2Multiply achieves up to 10x speedup, 3.8x higher GOPS/Watt, and 1.4x higher GOPS/area, while the RTM counterpart offers gains of 10x, 57x, and 3.8x., Comment: 14 pages

In today's data-centric world, where data fuels numerous application domains, with machine learning at the forefront, handling the enormous volume of data efficiently in terms of time and energy presents a formidable challenge. Conventional computing systems and accelerators are continually being pushed to their limits to stay competitive. In this context, computing near-memory (CNM) and computing-in-memory (CIM) have emerged as potentially game-changing paradigms. This survey introduces the basics of CNM and CIM architectures, including their underlying technologies and working principles. We focus particularly on CIM and CNM architectures that have either been prototyped or commercialized. While surveying the evolving CIM and CNM landscape in academia and industry, we discuss the potential benefits in terms of performance, energy, and cost, along with the challenges associated with these cutting-edge computing paradigms.

The accuracy of neural networks has greatly improved across various domains over the past years. Their ever-increasing complexity, however, leads to prohibitively high energy demands and latency in von Neumann systems. Several computing-in-memory (CIM) systems have recently been proposed to overcome this, but trade-offs involving accuracy, hardware reliability, and scalability for large models remain a challenge. Additionally, for some CIM designs, the activation movement still requires considerable time and energy. This paper explores the combination of algorithmic optimizations for ternary weight neural networks and associative processors (APs) implemented using racetrack memory (RTM). We propose a novel compilation flow to optimize convolutions on APs by reducing their arithmetic intensity. By leveraging the benefits of RTM-based APs, this approach substantially reduces data transfers within the memory while addressing accuracy, energy efficiency, and reliability concerns. Concretely, our solution improves the energy efficiency of ResNet-18 inference on ImageNet by 7.5x compared to crossbar in-memory accelerators while retaining software accuracy., Comment: To be presented at DATE24

Machine learning and data analytics applications increasingly suffer from the high latency and energy consumption of conventional von Neumann architectures. Recently, several in-memory and near-memory systems have been proposed to remove this von Neumann bottleneck. Platforms based on content-addressable memories (CAMs) are particularly interesting due to their efficient support for the search-based operations that form the foundation for many applications, including K-nearest neighbors (KNN), high-dimensional computing (HDC), recommender systems, and one-shot learning among others. Today, these platforms are designed by hand and can only be programmed with low-level code, accessible only to hardware experts. In this paper, we introduce C4CAM, the first compiler framework to quickly explore CAM configurations and to seamlessly generate code from high-level TorchScript code. C4CAM employs a hierarchy of abstractions that progressively lowers programs, allowing code transformations at the most suitable abstraction level. Depending on the type and technology, CAM arrays exhibit varying latencies and power profiles. Our framework allows analyzing the impact of such differences in terms of system-level performance and energy consumption, and thus supports designers in selecting appropriate designs for a given application., Comment: 10 pages, 9 figures

We unveil how generalizable AI can be used to improve multi-view 3D pedestrian detection in unlabeled target scenes. One way to increase generalization to new scenes is to automatically label target data, which can then be used for training a detector model. In this context, we investigate two approaches for automatically labeling target data: pseudo-labeling using a supervised detector and automatic labeling using an untrained detector (that can be applied out of the box without any training). We adopt a training framework for optimizing detector models using automatic labeling procedures. This framework encompasses different training sets/modes and multi-round automatic labeling strategies. We conduct our analyses on the publicly-available WILDTRACK and MultiviewX datasets. We show that, by using the automatic labeling approach based on an untrained detector, we can obtain superior results than directly using the untrained detector or a detector trained with an existing labeled source dataset. It achieved a MODA about 4% and 1% better than the best existing unlabeled method when using WILDTRACK and MultiviewX as target datasets, respectively., Comment: Accepted to SIBGRAPI 2023

The conventional approach to data-driven inversion framework is based on Gaussian statistics that presents serious difficulties, especially in the presence of outliers in the measurements. In this work, we present maximum likelihood estimators associated with generalized Gaussian distributions in the context of R\'enyi, Tsallis and Kaniadakis statistics. In this regard, we analytically analyse the outlier-resistance of each proposal through the so-called influence function. In this way, we formulate inverse problems by constructing objective functions linked to the maximum likelihood estimators. To demonstrate the robustness of the generalized methodologies, we consider an important geophysical inverse problem with high noisy data with spikes. The results reveal that the best data inversion performance occurs when the entropic index from each generalized statistic is associated with objective functions proportional to the inverse of the error amplitude. We argue that in such a limit the three approaches are resistant to outliers and are also equivalent, which suggests a lower computational cost for the inversion process due to the reduction of numerical simulations to be performed and the fast convergence of the optimization process., Comment: 17 pages, 14 figures

The shape and motion of the heart provide essential clues to understanding the mechanisms of cardiovascular disease. With the advent of large-scale cardiac imaging data, statistical atlases become a powerful tool to provide automated and precise quantification of the status of patient-specific heart geometry with respect to reference populations. The Multi-Ethnic Study of Atherosclerosis (MESA), begun in 2000, was the first large cohort study to incorporate cardiovascular MRI in over 5000 participants, and there is now a wealth of follow-up data over 20 years. Building a machine learning based automated analysis is necessary to extract the additional imaging information necessary for expanding original manual analyses. However, machine learning tools trained on MRI datasets with different pulse sequences fail on such legacy datasets. Here, we describe an automated atlas construction pipeline using deep learning methods applied to the legacy cardiac MRI data in MESA. For detection of anatomical cardiac landmark points, a modified VGGNet convolutional neural network architecture was used in conjunction with a transfer learning sequence between two-chamber, four-chamber, and short-axis MRI views. A U-Net architecture was used for detection of the endocardial and epicardial boundaries in short axis images. Both network architectures resulted in good segmentation and landmark detection accuracies compared with inter-observer variations. Statistical relationships with common risk factors were similar between atlases derived from automated vs manual annotations. The automated atlas can be employed in future studies to examine the relationships between cardiac morphology and future events.