Soft pneumatic actuators are used to steer soft growing "vine" robots while being flexible enough to undergo the tip eversion required for growth. In this study, we compared the performance of three types of pneumatic actuators in terms of their ability to perform eversion, quasi-static bending, dynamic motion, and force output: the pouch motor, the cylindrical pneumatic artificial muscle (cPAM), and the fabric pneumatic artificial muscle (fPAM). The pouch motor is advantageous for prototyping due to its simple manufacturing process. The cPAM exhibits superior bending behavior and produces the highest forces, while the fPAM actuates fastest and everts at the lowest pressure. We evaluated a range of dimensions for each actuator type. Larger actuators can produce more significant deformations and forces, but smaller actuators inflate faster and can evert at a lower pressure. Because vine robots are lightweight, the effect of gravity on the functionality of different actuators is minimal. We developed a new analytical model that predicts the pressure-to-bending behavior of vine robot actuators. Using the actuator results, we designed and demonstrated a 4.8 m long vine robot equipped with highly maneuverable 60x60 mm cPAMs in a three-dimensional obstacle course. The vine robot was able to move around sharp turns, travel through a passage smaller than its diameter, and lift itself against gravity.

This paper presents a computational framework for the concise encoding of an ensemble of persistence diagrams, in the form of weighted Wasserstein barycenters [100], [102] of a dictionary of atom diagrams. We introduce a multi-scale gradient descent approach for the efficient resolution of the corresponding minimization problem, which interleaves the optimization of the barycenter weights with the optimization of the atom diagrams. Our approach leverages the analytic expressions for the gradient of both sub-problems to ensure fast iterations and it additionally exploits shared-memory parallelism. Extensive experiments on public ensembles demonstrate the efficiency of our approach, with Wasserstein dictionary computations in the orders of minutes for the largest examples. We show the utility of our contributions in two applications. First, we apply Wassserstein dictionaries to data reduction and reliably compress persistence diagrams by concisely representing them with their weights in the dictionary. Second, we present a dimensionality reduction framework based on a Wasserstein dictionary defined with a small number of atoms (typically three) and encode the dictionary as a low dimensional simplex embedded in a visual space (typically in 2D). In both applications, quantitative experiments assess the relevance of our framework. Finally, we provide a C++ implementation that can be used to reproduce our results.

Answering questions related to the legal domain is a complex task, primarily due to the intricate nature and diverse range of legal document systems. Providing an accurate answer to a legal query typically necessitates specialized knowledge in the relevant domain, which makes this task all the more challenging, even for human experts. Question answering (QA) systems are designed to generate answers to questions asked in human languages. QA uses natural language processing to understand questions and search through information to find relevant answers. QA has various practical applications, including customer service, education, research, and cross-lingual communication. However, QA faces challenges such as improving natural language understanding and handling complex and ambiguous questions. Answering questions related to the legal domain is a complex task, primarily due to the intricate nature and diverse range of legal document systems. Providing an accurate answer to a legal query typically necessitates specialized knowledge in the relevant domain, which makes this task all the more challenging, even for human experts. At this time, there is a lack of surveys that discuss legal question answering. To address this problem, we provide a comprehensive survey that reviews 14 benchmark datasets for question-answering in the legal field as well as presents a comprehensive review of the state-of-the-art Legal Question Answering deep learning models. We cover the different architectures and techniques used in these studies and the performance and limitations of these models. Moreover, we have established a public GitHub repository where we regularly upload the most recent articles, open data, and source code. The repository is available at: \url{https://github.com/abdoelsayed2016/Legal-Question-Answering-Review}.

Deep neural networks use skip connections to improve training convergence. However, these skip connections are costly in hardware, requiring extra buffers and increasing on- and off-chip memory utilization and bandwidth requirements. In this paper, we show that skip connections can be optimized for hardware when tackled with a hardware-software codesign approach. We argue that while a network's skip connections are needed for the network to learn, they can later be removed or shortened to provide a more hardware efficient implementation with minimal to no accuracy loss. We introduce Tailor, a codesign tool whose hardware-aware training algorithm gradually removes or shortens a fully trained network's skip connections to lower their hardware cost. Tailor improves resource utilization by up to 34% for BRAMs, 13% for FFs, and 16% for LUTs for on-chip, dataflow-style architectures. Tailor increases performance by 30% and reduces memory bandwidth by 45% for a 2D processing element array architecture.

Deep Nonnegative Matrix Factorization (deep NMF) has recently emerged as a valuable technique for extracting multiple layers of features across different scales. However, all existing deep NMF models and algorithms have primarily centered their evaluation on the least squares error, which may not be the most appropriate metric for assessing the quality of approximations on diverse datasets. For instance, when dealing with data types such as audio signals and documents, it is widely acknowledged that $\beta$-divergences offer a more suitable alternative. In this paper, we develop new models and algorithms for deep NMF using $\beta$-divergences. Subsequently, we apply these techniques to the extraction of facial features, the identification of topics within document collections, and the identification of materials within hyperspectral images.

In real-world classification settings, such as loan application evaluation or content moderation on online platforms, individuals respond to classifier predictions by strategically updating their features to increase their likelihood of receiving a particular (positive) decision (at a certain cost). Yet, when different demographic groups have different feature distributions or pay different update costs, prior work has shown that individuals from minority groups often pay a higher cost to update their features. Fair classification aims to address such classifier performance disparities by constraining the classifiers to satisfy statistical fairness properties. However, we show that standard fairness constraints do not guarantee that the constrained classifier reduces the disparity in strategic manipulation cost. To address such biases in strategic settings and provide equal opportunities for strategic manipulation, we propose a constrained optimization framework that constructs classifiers that lower the strategic manipulation cost for minority groups. We develop our framework by studying theoretical connections between group-specific strategic cost disparity and standard selection rate fairness metrics (e.g., statistical rate and true positive rate). Empirically, we show the efficacy of this approach over multiple real-world datasets.

The Department of Homeland Security (DHS) on Thursday unveiled new guardrails for its use of artificial intelligence in carrying out its mission to secure the border. The new policies were developed by DHS Artificial Intelligence Task Force (AITF), which DHS Secretary Alejandro Mayorkas created in April. In announcing these new policies, DHS noted that AI has been critical to its missions, including combating fentanyl trafficking, strengthening supply chain security, countering sexual exploitation, and protecting critical infrastructure. The Department of Homeland Security logo is seen during a news conference in Washington. Mayorkas writes in the AI policy memo, expected to be released later Thursday, that the US must ensure AI is "rigorously tested to be effective [and] safeguards privacy, civil rights, and civil liberties while avoiding inappropriate biases."

FOX News Los Angeles-based chief correspondent Jonathan Hunt has more on the revelations on'Special Report.' NASA announced Thursday it has appointed a new director of unidentified anomalous phenomena (UAP) research in an effort by the space agency to better understand what it describes as "one of our planet's greatest mysteries." The new position, according to NASA, will "centralize communications, resources and data analytical capabilities to establish a robust database for the evaluation of future UAP," which is the government's terminology when referring to UFOs. "NASA's new director of UAP research will develop and oversee the implementation of NASA's scientific vision for UAP research, including using NASA's expertise to work with other agencies to analyze UAP and applying artificial intelligence and machine learning to search the skies for anomalies," NASA Administrator Bill Nelson said in a statement. "NASA will do this work transparently for the benefit of humanity."

The CEOs of leading AI companies -- including Meta's Mark Zuckerberg, Microsoft's Satya Nadella, Alphabet's Sundar Pichai, Tesla's Elon Musk and Open AI's Sam Altman -- appeared before Congress once again on Wednesday. But instead of the normal bombast and soapboxing we see during public hearings about the dangers of unfettered AI development, this conversation reportedly took on far more muted tones. In all, more than 20 tech and civil society leaders spoke with lawmakers at Wednesday's meeting, organized by Senate Majority Leader Chuck Schumer, to discuss how AI development should be regulated moving forward. Senators Martin Heinrich (D-NM), Todd Young (R-IN) and Mike Rounds (R-SD) who were also in attendance and reportedly working with the majority leader to draft additional proposals. "First, I asked everyone in the room, 'Is government needed to play a role in regulating AI?' and every single person raised their hands even though they had diverse views," Schumer told reporters Wednesday.

US senators are proving slow studies when it comes to the generative artificial intelligence tools that are poised to upend life as we know it. But they'll be tested soon--and the rest of us through them--if their new private tutors are to be trusted. In a historic first, yesterday upwards of 60 senators sat like school children--not allowed to speak or even raise their hands--in a private briefing where some 20 Silicon Valley CEOs, ethicists, academics, and consumer advocates prophesied about AI's potential to upend, heal, or even erase life as we knew it. "It's important for us to have a referee," Elon Musk, the CEO of Tesla, SpaceX, and X (formerly Twitter), told a throng of paparazzi-like press corps waiting on the sidewalk outside the briefing. "[It] may go down in history as very important to the future of civilization."