Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes decision-making scenarios is still limited due to the potential for errors. Selective prediction is a technique that can be used to improve the reliability of the LLMs by allowing them to abstain from making predictions when they are unsure of the answer. In this work, we propose a novel framework for adaptation with self-evaluation to improve the selective prediction performance of LLMs. Our framework is based on the idea of using parameter-efficient tuning to adapt the LLM to the specific task at hand while improving its ability to perform self-evaluation. We evaluate our method on a variety of question-answering (QA) datasets and show that it outperforms state-of-the-art selective prediction methods. For example, on the CoQA benchmark, our method improves the AUACC from 91.23% to 92.63% and improves the AUROC from 74.61% to 80.25%.

The usage of Lithium-ion (Li-ion) batteries has gained widespread popularity across various industries, from powering portable electronic devices to propelling electric vehicles and supporting energy storage systems. A central challenge in Li-ion battery reliability lies in accurately predicting their Remaining Useful Life (RUL), which is a critical measure for proactive maintenance and predictive analytics. This study presents a novel approach that harnesses the power of multiple denoising modules, each trained to address specific types of noise commonly encountered in battery data. Specifically, a denoising auto-encoder and a wavelet denoiser are used to generate encoded/decomposed representations, which are subsequently processed through dedicated self-attention transformer encoders. After extensive experimentation on NASA and CALCE data, a broad spectrum of health indicator values are estimated under a set of diverse noise patterns. The reported error metrics on these data are on par with or better than the state-of-the-art reported in recent literature.

Machine learning (ML) is widely used for key tasks in Connected and Automated Vehicles (CAV), including perception, planning, and control. However, its reliance on vehicular data for model training presents significant challenges related to in-vehicle user privacy and communication overhead generated by massive data volumes. Federated learning (FL) is a decentralized ML approach that enables multiple vehicles to collaboratively develop models, broadening learning from various driving environments, enhancing overall performance, and simultaneously securing local vehicle data privacy and security. This survey paper presents a review of the advancements made in the application of FL for CAV (FL4CAV). First, centralized and decentralized frameworks of FL are analyzed, highlighting their key characteristics and methodologies. Second, diverse data sources, models, and data security techniques relevant to FL in CAVs are reviewed, emphasizing their significance in ensuring privacy and confidentiality. Third, specific applications of FL are explored, providing insight into the base models and datasets employed for each application. Finally, existing challenges for FL4CAV are listed and potential directions for future investigation to further enhance the effectiveness and efficiency of FL in the context of CAV are discussed.

The IDF says it forces "destroyed an underground tunnel shaft containing ready-to-use explosive devices. It also said that "additional weapons were found, as well as ammunition and military equipment." JERUSALEM - Israel Defense Forces (IDF) on Wednesday launched a raid on the city of Jenin and its refugee camp - two strongholds of Palestinian terrorist activity - in the West Bank. The IDF operation in the West Bank, known by Israelis by its biblical name Judea and Samaria, raises questions about the opening of a third front in Israel's response to Hamas' multipronged attack against the Jewish state on Oct. 7, resulting in the massacre of 1,400 people in southern Israel. The IDF said in a statement that its counterterrorism forces "exchanged fire with armed terrorists, over ten terrorists were killed, and over 20 wanted suspects were apprehended, among them Nur and Minur Salma, Palestinian Islamic Jihad terrorists." The U.S. has designated the Iran-backed Palestinian Islamic Jihad a foreign terrorist organization. The fighting comes at a time when the Biden administration is cautioning Israeli actions in the West Bank, especially when it comes to violence from a small group of extremist settlers who have been involved in armed confrontations with Palestinian villagers in the area. NETANYAHU TELLS BRET BAIER CEASE-FIRE'MEANS SURRENDER,' INSISTS SQUAD MEMBER IS CALLING FOR'GENOCIDE' Palestinian terrorists take up position during a confrontation with the Israeli army in Jenin on July 3, 2023. The Israeli army said it had launched drone strikes in Jenin as part of an "extensive counterterrorism effort." U.S. Secretary of State Antony Blinken said on Monday in Tokyo at the G-7 meeting that "I briefed by (sic) colleagues about my conversations with Israeli leaders on pauses, and on concrete steps to minimize harm to Palestinian civilians in Gaza and to stop extremist violence in the West Bank." The Associated Press reported that President Biden said in late October the attacks by "extremist settlers" amounted to "pouring gasoline" on the already burning fires in the Middle East since the Hamas attack. The administration refers to Jewish residents who live in the disputed West Bank territory as settlers. Following Thursday's raid, the IDF added that "Two M-16 rifles, a'Carlo' gun, three handguns, ammunition, and military equipment were seized." The Palestinian-manufactured "Carlo" gun has its origins in the 2016 terrorism wave against Israelis. The weapon is a watered-down version of the Carl Gustav submachine gun - hence its name, the "Carlo" gun. "The initiative is always ours to prevent a third front.

The thread was 10 tweets long--verbose by X standards--and 219 words, but there was just one word that stuck out. The message, posted on the @SAG-AFTRA account, summed up everything the actors union had fought to get in the tentative agreement with Hollywood studios. In the context of the rapid rise of generative AI, it's worth reading in full: "We have achieved a deal of extraordinary scope that includes'above-pattern' minimum compensation increases, unprecedented provisions for consent and compensation that will protect members from the threat of AI, and for the first time establishes a streaming participation bonus." "Threat," of course, is how many people have come to view artificial intelligence. US president Joe Biden's recent executive order on the technology was seen as, in part, a way to address the risks the technology presents to national security.

Francesca Mani and her mother Dorota join'The Ingraham Angle' to demand accountability for victims. One New Jersey mother is fighting to change laws regarding Artificial Intelligence (AI), after her daughter's face was used to generate a fake nude image and reportedly circulated among her classmates. Dorota Mani says her 14-year-old daughter Francesca was one of several female students at Westfield High, N.J., whose photo was used by another classmate to create the pornographic images using AI. While the girls and the school were made aware of the incident in October, the images were shared last summer. Mani told Fox News Digital that she filed a police report and has been in contact with Westfield High over the incident.

United States troops in Iraq have been targeted in new attacks using drones and explosives, according to military and security sources. Three attacks took place on Thursday, the sources said, adding to the more than 40 assaults that US and allied troops based across the Middle East have come under since the Israel-Hamas war started on October 7. As well as two drone assaults at bases, a US-led coalition convoy was hit by an improvised explosive device (IED) blast in the vicinity of Mosul Dam. The security sources said the patrol was accompanied by Iraqi counterterrorism forces and that a vehicle in the patrol was damaged. Three US troops sustained minor injuries but had returned to duty, the official added.

Diagnosing knee joint osteoarthritis (KOA), a major cause of disability worldwide, is challenging due to subtle radiographic indicators and the varied progression of the disease. Using deep learning for KOA diagnosis requires broad, comprehensive datasets. However, obtaining these datasets poses significant challenges due to patient privacy concerns and data collection restrictions. Additive data augmentation, which enhances data variability, emerges as a promising solution. Yet, it's unclear which augmentation techniques are most effective for KOA. This study explored various data augmentation methods, including adversarial augmentations, and their impact on KOA classification model performance. While some techniques improved performance, others commonly used underperformed. We identified potential confounding regions within the images using adversarial augmentation. This was evidenced by our models' ability to classify KL0 and KL4 grades accurately, with the knee joint omitted. This observation suggested a model bias, which might leverage unrelated features for classification currently present in radiographs. Interestingly, removing the knee joint also led to an unexpected improvement in KL1 classification accuracy. To better visualize these paradoxical effects, we employed Grad-CAM, highlighting the associated regions. Our study underscores the need for careful technique selection for improved model performance and identifying and managing potential confounding regions in radiographic KOA deep learning.

In the realm of machine and deep learning regression tasks, the role of effective feature engineering (FE) is pivotal in enhancing model performance. Traditional approaches of FE often rely on domain expertise to manually design features for machine learning models. In the context of deep learning models, the FE is embedded in the neural network's architecture, making it hard for interpretation. In this study, we propose to integrate symbolic regression (SR) as an FE process before a machine learning model to improve its performance. We show, through extensive experimentation on synthetic and real-world physics-related datasets, that the incorporation of SR-derived features significantly enhances the predictive capabilities of both machine and deep learning regression models with 34-86% root mean square error (RMSE) improvement in synthetic datasets and 4-11.5% improvement in real-world datasets. In addition, as a realistic use-case, we show the proposed method improves the machine learning performance in predicting superconducting critical temperatures based on Eliashberg theory by more than 20% in terms of RMSE. These results outline the potential of SR as an FE component in data-driven models.

Manual ontology construction takes time, resources, and domain specialists. Supporting a component of this process for automation or semi-automation would be good. This project and dissertation provide a Formal Concept Analysis and WordNet framework for learning concept hierarchies from free texts. The process has steps. First, the document is Part-Of-Speech labeled, then parsed to produce sentence parse trees. Verb/noun dependencies are derived from parse trees next. After lemmatizing, pruning, and filtering the word pairings, the formal context is created. The formal context may contain some erroneous and uninteresting pairs because the parser output may be erroneous, not all derived pairs are interesting, and it may be large due to constructing it from a large free text corpus. Deriving lattice from the formal context may take longer, depending on the size and complexity of the data. Thus, decreasing formal context may eliminate erroneous and uninteresting pairs and speed up idea lattice derivation. WordNet-based and Frequency-based approaches are tested. Finally, we compute formal idea lattice and create a classical concept hierarchy. The reduced concept lattice is compared to the original to evaluate the outcomes. Despite several system constraints and component discrepancies that may prevent logical conclusion, the following data imply idea hierarchies in this project and dissertation are promising. First, the reduced idea lattice and original concept have commonalities. Second, alternative language or statistical methods can reduce formal context size. Finally, WordNet-based and Frequency-based approaches reduce formal context differently, and the order of applying them is examined to reduce context efficiently.