Search

Deep neural networks (DNNs) offer significant promise for improving breast cancer diagnosis in medical imaging. However, these models are highly susceptible to adversarial attacks--small, imperceptible changes that can mislead classifiers--raising critical concerns about their reliability and security. Traditional attacks rely on fixed-norm perturbations, misaligning with human perception. In contrast, diffusion-based attacks require pre-trained models, demanding substantial data when these models are unavailable, limiting practical use in data-scarce scenarios. In medical imaging, however, this is often unfeasible due to the limited availability of datasets. Building on recent advancements in learnable prompts, we propose Prompt2Perturb (P2P), a novel language-guided attack method capable of generating meaningful attack examples driven by text instructions. During the prompt learning phase, our approach leverages learnable prompts within the text encoder to create subtle, yet impactful, perturbations that remain imperceptible while guiding the model towards targeted outcomes. In contrast to current prompt learning-based approaches, our P2P stands out by directly updating text embeddings, avoiding the need for retraining diffusion models. Further, we leverage the finding that optimizing only the early reverse diffusion steps boosts efficiency while ensuring that the generated adversarial examples incorporate subtle noise, thus preserving ultrasound image quality without introducing noticeable artifacts. We show that our method outperforms state-of-the-art attack techniques across three breast ultrasound datasets in FID and LPIPS. Moreover, the generated images are both more natural in appearance and more effective compared to existing adversarial attacks. Our code will be publicly available https://github.com/yasamin-med/P2P.

Ensuring that Software Requirements Specifications (SRS) align with higher-level organizational or national requirements is vital, particularly in regulated environments such as finance and aerospace. In these domains, maintaining consistency, adhering to regulatory frameworks, minimizing errors, and meeting critical expectations are essential for the reliable functioning of systems. The widespread adoption of large language models (LLMs) highlights their immense potential, yet there remains considerable scope for improvement in retrieving relevant information and enhancing reasoning capabilities. This study demonstrates that integrating a robust Graph-RAG framework with advanced prompt engineering techniques, such as Chain of Thought and Tree of Thought, can significantly enhance performance. Compared to baseline RAG methods and simple prompting strategies, this approach delivers more accurate and context-aware results. While this method demonstrates significant improvements in performance, it comes with challenges. It is both costly and more complex to implement across diverse contexts, requiring careful adaptation to specific scenarios. Additionally, its effectiveness heavily relies on having complete and accurate input data, which may not always be readily available, posing further limitations to its scalability and practicality.

While Online Learning is growing and becoming widespread, the associated curricula often suffer from a lack of coverage and outdated content. In this regard, a key question is how to dynamically define the topics that must be covered to thoroughly learn a subject (e.g., a course). Large Language Models (LLMs) are considered candidates that can be used to address curriculum development challenges. Therefore, we developed a framework and a novel dataset, built on YouTube, to evaluate LLMs' performance when it comes to generating learning topics for specific courses. The experiment was conducted across over 100 courses and nearly 7,000 YouTube playlists in various subject areas. Our results indicate that GPT-4 can produce more accurate topics for the given courses than extracted topics from YouTube video playlists in terms of BERTScore

Dielectric loaded waveguides (DLWs) driven by multicycle terahertz (THz) pulses hold great promise as compact linear accelerators (LINACs) due to their ability to sustain higher breakdown fields at THz frequencies compared to conventional RF components. Precise control of the THz pulse's phase and group velocities within the DLW can be achieved by adjusting the dimensions of the dielectric tube. Optimization of the DLW parameters has to take various factors into account like initial electron energy, THz pulse energy available, THz pulse width, DLW dimensions, etc. To maximize the final kinetic energy of the accelerated electrons, this study presents a comprehensive analytical/numerical guideline for cylindrical DLW LINACs. Additionally, graphic representations are introduced to visualize optimal designs for varying initial electron and THz pulse energies. The provided guideline figures enable designers to tailor the accelerator to specific requirements, paving the way for potential advancements in THz-driven particle acceleration and offering cost-effective alternatives to conventional RF accelerators for various scientific, industrial, and medical applications.

We present a systematic analysis of the spatially resolved star formation histories (SFHs) using Hubble Space Telescope imaging data of $\sim 997$, intermediate redshifts $0.5 \leq z \leq 2.0$ galaxies from the GOODS-S field, with stellar mass range $9.8 \leq \log \mathrm{M}_{\star}/\mathrm{M}_{\odot} \leq 11.5$. We estimate the SFHs in three spatial regions (central region within the half-mass radii $\mathrm{R}_{50s}$, outskirts between $1-3~\mathrm{R}_{50s}$, and the whole galaxy) using pixel-by-pixel spectral-energy distribution (SED) fitting, assuming exponentially declining tau model in individual pixels. The reconstructed SFHs are then used to derive and compare the physical properties such as specific star-formation rates (sSFRs), mass-weighted ages (t$_{\mathrm{50}}$), and the half-mass radii to get insights on the interplay between the structure and star-formation in galaxies. The correlation of sSFR ratio of the center and outskirts with the distance from the main sequence (MS) indicates that galaxies on the upper envelope of the MS tend to grow outside-in, building up their central regions, while those below the MS grow inside-out, with more active star formation in the outskirts. The findings suggest a self-regulating process in galaxy size growth when they evolve along the MS. Our observations are consistent with galaxies growing their inner bulge and outer disc regions, where they appear to oscillate about the average MS in cycles of central gas compaction, which leads to bulge growth, and subsequent central depletion possibly due to feedback from the starburst, resulting in more star formation towards the outskirts from newly accreted gas., Comment: 12 pages, 8 figures

Social support, conveyed through a multitude of interactions and platforms such as social media, plays a pivotal role in fostering a sense of belonging, aiding resilience in the face of challenges, and enhancing overall well-being. This paper introduces Social Support Detection (SSD) as a Natural language processing (NLP) task aimed at identifying supportive interactions within online communities. The study presents the task of Social Support Detection (SSD) in three subtasks: two binary classification tasks and one multiclass task, with labels detailed in the dataset section. We conducted experiments on a dataset comprising 10,000 YouTube comments. Traditional machine learning models were employed, utilizing various feature combinations that encompass linguistic, psycholinguistic, emotional, and sentiment information. Additionally, we experimented with neural network-based models using various word embeddings to enhance the performance of our models across these subtasks.The results reveal a prevalence of group-oriented support in online dialogues, reflecting broader societal patterns. The findings demonstrate the effectiveness of integrating psycholinguistic, emotional, and sentiment features with n-grams in detecting social support and distinguishing whether it is directed toward an individual or a group. The best results for different subtasks across all experiments range from 0.72 to 0.82.

Monitored quantum circuits offer great perspectives for exploring the interplay of quantum information and complex quantum dynamics. These systems could realize the extensively studied entanglement and purification phase transitions, as well as a rich variety of symmetry-protected and ordered non-equilibrium phases. The central question regarding such phases is whether they survive in real-world devices exhibiting unavoidable symmetry-breaking noise. We study the fate of the symmetry-protected absorbing state and charge-sharpening transitions in the presence of symmetry-breaking noise, and establish that the net effect of noise results in coherent and incoherent symmetry-breaking effects. The coherent contribution removes a sharp distinction between different phases and renders phase transitions to crossovers. Nevertheless, states far away from the original phase boundaries retain their essential character. In fact, corrective feedback in adaptive quantum circuits and postselected measurements in symmetric charge-conserving quantum circuits can suppress the effects of noise, thereby stabilizing the absorbing and charge-sharp phases, respectively. Despite the unavoidable noise in current quantum hardwares, our findings offer an optimistic outlook for observing symmetry-protected phases in currently available Noisy Intermediate-Scale Quantum (NISQ) devices. Moreover, our work suggests a symmetry-based benchmarking method as an alternative for characterizing noise and evaluating average local gate fidelity., Comment: 13 pages, 6 figures

We aim to discern scenarios of structural evolution of intermediate to high-mass star-forming galaxies (SFGs) since cosmic noon by comparing their stellar mass profiles with present-day stellar masses of $\log(M_{\ast,0}/M_{\odot})=10.3-11$. We addressed discrepancies in the size evolution rates of SFGs, which may be caused by variations in sample selection and methods for size measurements. To check these factors, we traced the evolution of individual galaxies by identifying their progenitors using stellar mass growth histories (SMGHs), integrating along the star-forming main sequence and from the IllustrisTNG simulations. Comparison between the structural parameters estimated from the mass- and light-based profiles shows that mass-weighted size evolves at a slower pace compared to light-based ones, highlighting the need to consider the mass-to-light ratio ($M/L$) gradients. Additionally, we observed mass-dependent growth in stellar mass profiles: massive galaxies ($\log(M_{\ast,0}/M_{\odot})\gtrsim10.8$) formed central regions at $z\gtrsim1.5$ and grew faster in outer regions, suggesting inside-out growth, while intermediate and less massive SFGs followed a relatively self-similar mass buildup since $z\sim2$. Moreover, slopes of observed size evolution conflict with the predictions of TNG50 for samples selected using the same SMGHs across our redshift range. To explore the origin of this deviation, we examined changes in angular momentum (AM) retention fraction using the half-mass size evolution and employing a simple disk formation model. Assuming similar dark matter halo parameters, our calculations indicate that the AM inferred from observations halved in the last 10 Gyr while it remained relatively constant in TNG50. This higher AM in simulations may be due to the accretion of high-AM gases into disks., Comment: Accepted for publication in ApJ; 25 pages, 11 figures

We introduce Learning from Offline Foundation Features with Tensor Augmentations (LOFF-TA), an efficient training scheme designed to harness the capabilities of foundation models in limited resource settings where their direct development is not feasible. LOFF-TA involves training a compact classifier on cached feature embeddings from a frozen foundation model, resulting in up to $37\times$ faster training and up to $26\times$ reduced GPU memory usage. Because the embeddings of augmented images would be too numerous to store, yet the augmentation process is essential for training, we propose to apply tensor augmentations to the cached embeddings of the original non-augmented images. LOFF-TA makes it possible to leverage the power of foundation models, regardless of their size, in settings with limited computational capacity. Moreover, LOFF-TA can be used to apply foundation models to high-resolution images without increasing compute. In certain scenarios, we find that training with LOFF-TA yields better results than directly fine-tuning the foundation model., Comment: Accepted to the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

We introduce Temporal Attention-enhanced Variational Graph Recurrent Neural Network (TAVRNN), a novel framework for analyzing the evolving dynamics of neuronal connectivity networks in response to external stimuli and behavioral feedback. TAVRNN captures temporal changes in network structure by modeling sequential snapshots of neuronal activity, enabling the identification of key connectivity patterns. Leveraging temporal attention mechanisms and variational graph techniques, TAVRNN uncovers how connectivity shifts align with behavior over time. We validate TAVRNN on two datasets: in vivo calcium imaging data from freely behaving rats and novel in vitro electrophysiological data from the DishBrain system, where biological neurons control a simulated environment during the game of pong. We show that TAVRNN outperforms previous baseline models in classification, clustering tasks and computational efficiency while accurately linking connectivity changes to performance variations. Crucially, TAVRNN reveals that high game performance in the DishBrain system correlates with the alignment of sensory and motor subregion channels, a relationship not evident in earlier models. This framework represents the first application of dynamic graph representation of electrophysiological (neuronal) data from DishBrain system, providing insights into the reorganization of neuronal networks during learning. TAVRNN's ability to differentiate between neuronal states associated with successful and unsuccessful learning outcomes, offers significant implications for real-time monitoring and manipulation of biological neuronal systems., Comment: 31 pages, 6 figures, 4 supplemental figures, 4 tables, 8 supplemental tables

Implicit Neural Representation (INR), leveraging a neural network to transform coordinate input into corresponding attributes, has recently driven significant advances in several vision-related domains. However, the performance of INR is heavily influenced by the choice of the nonlinear activation function used in its multilayer perceptron (MLP) architecture. Multiple nonlinearities have been investigated; yet, current INRs face limitations in capturing high-frequency components, diverse signal types, and handling inverse problems. We have identified that these problems can be greatly alleviated by introducing a paradigm shift in INRs. We find that an architecture with learnable activations in initial layers can represent fine details in the underlying signals. Specifically, we propose SL$^{2}$A-INR, a hybrid network for INR with a single-layer learnable activation function, prompting the effectiveness of traditional ReLU-based MLPs. Our method performs superior across diverse tasks, including image representation, 3D shape reconstructions, inpainting, single image super-resolution, CT reconstruction, and novel view synthesis. Through comprehensive experiments, SL$^{2}$A-INR sets new benchmarks in accuracy, quality, and convergence rates for INR.

Implicit neural representations (INRs) use neural networks to provide continuous and resolution-independent representations of complex signals with a small number of parameters. However, existing INR models often fail to capture important frequency components specific to each task. To address this issue, in this paper, we propose a Fourier Kolmogorov Arnold network (FKAN) for INRs. The proposed FKAN utilizes learnable activation functions modeled as Fourier series in the first layer to effectively control and learn the task-specific frequency components. In addition, the activation functions with learnable Fourier coefficients improve the ability of the network to capture complex patterns and details, which is beneficial for high-resolution and high-dimensional data. Experimental results show that our proposed FKAN model outperforms three state-of-the-art baseline schemes, and improves the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) for the image representation task and intersection over union (IoU) for the 3D occupancy volume representation task, respectively., Comment: Submitted to ICASSP 2025

Quantum reservoir computing (QRC) is a low-complexity learning paradigm that combines the inherent dynamics of input-driven many-body quantum systems with classical learning techniques for nonlinear temporal data processing. Optimizing the QRC process and computing device is a complex task due to the dependence of many-body quantum systems to various factors. To explore this, we introduce a strongly interacting spin model on random regular graphs as the quantum component and investigate the interplay between static disorder, interactions, and graph connectivity, revealing their critical impact on quantum memory capacity and learnability accuracy. We tackle linear quantum and nonlinear classical tasks, and identify optimal learning and memory regimes through studying information localization, dynamical quantum correlations, and the many-body structure of the disordered Hamiltonian. In particular, we uncover the role of previously overlooked network connectivity and demonstrate how the presence of quantum correlations can significantly enhance the learning performance. Our findings thus provide guidelines for the optimal design of disordered analog quantum learning platforms.

This study performs analysis of Predictive statements, Hope speech, and Regret Detection behaviors within cryptocurrency-related discussions, leveraging advanced natural language processing techniques. We introduce a novel classification scheme named "Prediction statements," categorizing comments into Predictive Incremental, Predictive Decremental, Predictive Neutral, or Non-Predictive categories. Employing GPT-4o, a cutting-edge large language model, we explore sentiment dynamics across five prominent cryptocurrencies: Cardano, Binance, Matic, Fantom, and Ripple. Our analysis reveals distinct patterns in predictive sentiments, with Matic demonstrating a notably higher propensity for optimistic predictions. Additionally, we investigate hope and regret sentiments, uncovering nuanced interplay between these emotions and predictive behaviors. Despite encountering limitations related to data volume and resource availability, our study reports valuable discoveries concerning investor behavior and sentiment trends within the cryptocurrency market, informing strategic decision-making and future research endeavors.

Learning unknown processes affecting a quantum system reveals underlying physical mechanisms and enables suppression, mitigation, and correction of unwanted effects. Describing a general quantum process requires an exponentially large number of parameters. Measuring these parameters, when they are encoded in incompatible observables, is constrained by the uncertainty principle and requires exponentially many measurements. However, for Pauli channels, having access to an ideal quantum memory and entangling operations allows encoding parameters in commuting observables, thereby exponentially reducing measurement complexity. In practice, though, quantum memory and entangling operations are always noisy and introduce errors, making the advantage of using noisy quantum memory unclear. To address these challenges we introduce error-mitigated entanglement-enhanced learning and show, both theoretically and experimentally, that even with noise, there is a separation in efficiency between learning Pauli channels with and without entanglement with noisy quantum memory. We demonstrate our protocol's efficacy in examples including hypothesis testing with up to 64 qubits and learning inherent noise processes in a layer of parallel gates using up to 16 qubits on a superconducting quantum processor. Our protocol provides accurate and practical information about the process, with an overhead factor of $1.33 \pm 0.05$ per qubit, much smaller than the fundamental lower bound of 2 without entanglement with quantum memory. Our study demonstrates that entanglement with auxiliary noisy quantum memory combined with error mitigation considerably enhances the learning of quantum processes.

Electron emission from cathodes in high field gradients is a quantum tunneling effect. The 1928 Fowler-Nordheim field emission (FE) equation and the 1956 Murphy-Good FE equation have traditionally been key in describing cold field emissions, offering estimates for emitters for almost a century. Nevertheless, applying FE theory in practice is often constrained by the lack of data on the distribution and geometry of the emission sites. Predictions become more challenging with an uneven electric field distribution at the cathode surface. Consequently, FE formulations are frequently calibrated using current-voltage data after test, limiting their efficacy as true predictive models. This study develops an alternative model for field emission using a data-driven predictive approach based on (1) vast experimental data, (2) electrostatic simulations of the cathode surface, and (3) detailed material and geometry properties, which together overcome these limitations. The objective of this work is to develop and harness this comprehensive dataset to train a machine learning model capable of providing precise predictions of the cathode current in order to further the understanding and application of field emission phenomena. More than 259 hours of experimental data have been processed to train and benchmark some of the well-known machine learning models. After two stages of optimization, a coefficient of determination >98% is achieved in the prediction total field emission current using ensemble models.

Medical image segmentation involves identifying and separating object instances in a medical image to delineate various tissues and structures, a task complicated by the significant variations in size, shape, and density of these features. Convolutional neural networks (CNNs) have traditionally been used for this task but have limitations in capturing long-range dependencies. Transformers, equipped with self-attention mechanisms, aim to address this problem. However, in medical image segmentation it is beneficial to merge both local and global features to effectively integrate feature maps across various scales, capturing both detailed features and broader semantic elements for dealing with variations in structures. In this paper, we introduce MSA$^2$Net, a new deep segmentation framework featuring an expedient design of skip-connections. These connections facilitate feature fusion by dynamically weighting and combining coarse-grained encoder features with fine-grained decoder feature maps. Specifically, we propose a Multi-Scale Adaptive Spatial Attention Gate (MASAG), which dynamically adjusts the receptive field (Local and Global contextual information) to ensure that spatially relevant features are selectively highlighted while minimizing background distractions. Extensive evaluations involving dermatology, and radiological datasets demonstrate that our MSA$^2$Net outperforms state-of-the-art (SOTA) works or matches their performance. The source code is publicly available at https://github.com/xmindflow/MSA-2Net., Comment: Accepted at BMVC 2024. Supplementary materials included at the end of the main paper (3 pages, 2 figures, 1 table)

The growing demand for high-resolution maps across various applications has underscored the necessity of accurately segmenting building vectors from overhead imagery. However, current deep neural networks often produce raster data outputs, leading to the need for extensive post-processing that compromises the fidelity, regularity, and simplicity of building representations. In response, this paper introduces a novel deep convolutional neural network named OriCornerNet, which directly extracts delineated building polygons from input images. Specifically, our approach involves a deep model that predicts building footprint masks, corners, and orientation vectors that indicate directions toward adjacent corners. These predictions are then used to reconstruct an initial polygon, followed by iterative refinement using a graph convolutional network that leverages semantic and geometric features. Our method inherently generates simplified polygons by initializing the refinement process with predicted corners. Also, including geometric information from oriented corners contributes to producing more regular and accurate results. Performance evaluations conducted on SpaceNet Vegas and CrowdAI-small datasets demonstrate the competitive efficacy of our approach compared to the state-of-the-art in building segmentation from overhead imagery., Comment: 5 Pages, 4 Figures

Measurement-induced entanglement phase transitions in monitored quantum circuits have stimulated activity in a diverse research community. However, the study of measurement-induced dynamics, due to the requirement of exponentially complex postselection, has been experimentally limited to small or specially designed systems that can be efficiently simulated classically. We present a solution to this outstanding problem by introducing a scalable protocol in $U(1)$ symmetric circuits that facilitates the observation of entanglement phase transitions \emph{directly} from experimental data, without detailed assumptions of the underlying model or benchmarking with simulated data. Thus, the method is applicable to circuits which do not admit efficient classical simulation and allows a reconstruction of the full entanglement entropy curve with minimal theoretical input. Our approach relies on adaptive circuits and a steering protocol to approximate pure-state trajectories with mixed ensembles, from which one can efficiently filter out the subsystem $U(1)$ charge fluctuations of the target trajectory to obtain its entanglement entropy. The steering protocol replaces the exponential costs of postselection and state tomography with a scalable overhead which, for fixed accuracy $\epsilon$ and circuit size $L$, scales as $\mathcal{N}_s\sim L^{5/2}/\epsilon$., Comment: 13 pages, 8 figures

Sequence modeling plays a vital role across various domains, with recurrent neural networks being historically the predominant method of performing these tasks. However, the emergence of transformers has altered this paradigm due to their superior performance. Built upon these advances, transformers have conjoined CNNs as two leading foundational models for learning visual representations. However, transformers are hindered by the $\mathcal{O}(N^2)$ complexity of their attention mechanisms, while CNNs lack global receptive fields and dynamic weight allocation. State Space Models (SSMs), specifically the \textit{\textbf{Mamba}} model with selection mechanisms and hardware-aware architecture, have garnered immense interest lately in sequential modeling and visual representation learning, challenging the dominance of transformers by providing infinite context lengths and offering substantial efficiency maintaining linear complexity in the input sequence. Capitalizing on the advances in computer vision, medical imaging has heralded a new epoch with Mamba models. Intending to help researchers navigate the surge, this survey seeks to offer an encyclopedic review of Mamba models in medical imaging. Specifically, we start with a comprehensive theoretical review forming the basis of SSMs, including Mamba architecture and its alternatives for sequence modeling paradigms in this context. Next, we offer a structured classification of Mamba models in the medical field and introduce a diverse categorization scheme based on their application, imaging modalities, and targeted organs. Finally, we summarize key challenges, discuss different future research directions of the SSMs in the medical domain, and propose several directions to fulfill the demands of this field. In addition, we have compiled the studies discussed in this paper along with their open-source implementations on our GitHub repository., Comment: This is the first version of our survey, and the paper is currently under review

How do biological systems and machine learning algorithms compare in the number of samples required to show significant improvements in completing a task? We compared the learning efficiency of in vitro biological neural networks to the state-of-the-art deep reinforcement learning (RL) algorithms in a simplified simulation of the game `Pong'. Using DishBrain, a system that embodies in vitro neural networks with in silico computation using a high-density multi-electrode array, we contrasted the learning rate and the performance of these biological systems against time-matched learning from three state-of-the-art deep RL algorithms (i.e., DQN, A2C, and PPO) in the same game environment. This allowed a meaningful comparison between biological neural systems and deep RL. We find that when samples are limited to a real-world time course, even these very simple biological cultures outperformed deep RL algorithms across various game performance characteristics, implying a higher sample efficiency. Ultimately, even when tested across multiple types of information input to assess the impact of higher dimensional data input, biological neurons showcased faster learning than all deep reinforcement learning agents., Comment: 13 Pages, 6 Figures - 38 Supplementary Pages, 6 Supplementary Figures, 4 Supplementary Tables

Homograph disambiguation, the task of distinguishing words with identical spellings but different meanings, poses a substantial challenge in natural language processing. In this study, we introduce a novel dataset tailored for Persian homograph disambiguation. Our work encompasses a thorough exploration of various embeddings, evaluated through the cosine similarity method and their efficacy in downstream tasks like classification. Our investigation entails training a diverse array of lightweight machine learning and deep learning models for phonograph disambiguation. We scrutinize the models' performance in terms of Accuracy, Recall, and F1 Score, thereby gaining insights into their respective strengths and limitations. The outcomes of our research underscore three key contributions. First, we present a newly curated Persian dataset, providing a solid foundation for future research in homograph disambiguation. Second, our comparative analysis of embeddings highlights their utility in different contexts, enriching the understanding of their capabilities. Third, by training and evaluating a spectrum of models, we extend valuable guidance for practitioners in selecting suitable strategies for homograph disambiguation tasks. In summary, our study unveils a new dataset, scrutinizes embeddings through diverse perspectives, and benchmarks various models for homograph disambiguation. These findings empower researchers and practitioners to navigate the intricate landscape of homograph-related challenges effectively.

A matrix is said to have factor width at most $k$ if it can be written as a sum of positive semidefinite matrices that are non-zero only in a single $k \times k$ principal submatrix. We explore the ``factor-width-$k$ rank'' of a matrix, which is the minimum number of rank-$1$ matrices that can be used in such a factor-width-at-most-$k$ decomposition. We show that the factor width rank of a banded or arrowhead matrix equals its usual rank, but for other matrices they can differ. We also establish several bounds on the factor width rank of a matrix, including a tight connection between factor-width-$k$ rank and the $k$-clique covering number of a graph, and we discuss how the factor width and factor width rank change when taking Hadamard products and Hadamard powers., Comment: 23 pages

Kolmogorov-Arnold Networks (KANs) offer an efficient and interpretable alternative to traditional multi-layer perceptron (MLP) architectures due to their finite network topology. However, according to the results of Kolmogorov and Vitushkin, the representation of generic smooth functions by KAN implementations using analytic functions constrained to a finite number of cutoff points cannot be exact. Hence, the convergence of KAN throughout the training process may be limited. This paper explores the relevance of smoothness in KANs, proposing that smooth, structurally informed KANs can achieve equivalence to MLPs in specific function classes. By leveraging inherent structural knowledge, KANs may reduce the data required for training and mitigate the risk of generating hallucinated predictions, thereby enhancing model reliability and performance in computational biomedicine.

The silicon T centre's narrow, telecommunications-band optical emission, long spin coherence, and direct photonic integration have spurred interest in this emitter as a spin-photon interface for distributed quantum computing and networking. However, key parameters of the T centre's spin-selective optical transitions remain undetermined or ambiguous in literature. In this paper we present a Hamiltonian of the T centre TX state and determine key parameters of the optical transition from T$_0$ to TX$_0$ from a combined analysis of published results, density functional theory, and new spectroscopy. We resolve ambiguous values of the internal defect potential in the literature, and we present the first measurements of electrically tuned T centre emission. As a result, we provide a model of the T centre's optical and spin properties under strain, electric, and magnetic fields that can be utilized for realizing quantum technologies., Comment: 18 pages and 13 figures in the main manuscript with appendix included

This study delves into the relationship between emotional trends from X platform data and the market dynamics of well-known cryptocurrencies Cardano, Binance, Fantom, Matic, and Ripple over the period from October 2022 to March 2023. Leveraging SenticNet, we identified emotions like Fear and Anxiety, Rage and Anger, Grief and Sadness, Delight and Pleasantness, Enthusiasm and Eagerness, and Delight and Joy. Following data extraction, we segmented each month into bi-weekly intervals, replicating this process for price data obtained from Finance-Yahoo. Consequently, a comparative analysis was conducted, establishing connections between emotional trends observed across bi-weekly intervals and cryptocurrency prices, uncovering significant correlations between emotional sentiments and coin valuations.

Brain-computer interface systems and the recording of brain activity has garnered significant attention across a diverse spectrum of applications. EEG signals have emerged as a modality for recording neural electrical activity. Among the methodologies designed for feature extraction from EEG data, the method of RCSP has proven to be an approach, particularly in the context of MI tasks. RCSP exhibits efficacy in the discrimination and classification of EEG signals. In optimizing the performance of this method, our research extends to a comparative analysis with conventional CSP techniques, as well as optimized methodologies designed for similar applications. Notably, we employ the meta-heuristic multi-objective Strength Pareto Evolutionary Algorithm II (SPEA-II) as a pivotal component of our research paradigm. This is a state-of-the-art approach in the selection of an subset of channels from a multichannel EEG signal with MI tasks. Our main objective is to formulate an optimum channel selection strategy aimed at identifying the most pertinent subset of channels from the multi-dimensional electroencephalogram (EEG) signals. One of the primary objectives inherent to channel selection in the EEG signal analysis pertains to the reduction of the channel count, an approach that enhances user comfort when utilizing gel-based EEG electrodes. Additionally, within this research, we took benefit of ensemble learning models as a component of our decision-making. This technique serves to mitigate the challenges associated with overfitting, especially when confronted with an extensive array of potentially redundant EEG channels and data noise. Our findings not only affirm the performance of RCSP in MI-based BCI systems, but also underscore the significance of channel selection strategies and ensemble learning techniques in optimizing the performance of EEG signal classification.

Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and allows for the updating of knowledge without retraining the LLM. However, RAG does not guarantee valid responses if retrieval fails to identify the necessary information as the context for response generation. Also, if there is contradictory content, the RAG response will likely reflect only one of the two possible responses. Therefore, quantifying uncertainty in the retrieval process is crucial for ensuring RAG trustworthiness. In this report, we introduce a four-step framework for applying conformal prediction to quantify retrieval uncertainty in RAG frameworks. First, a calibration set of questions answerable from the knowledge base is constructed. Each question's embedding is compared against document embeddings to identify the most relevant document chunks containing the answer and record their similarity scores. Given a user-specified error rate ({\alpha}), these similarity scores are then analyzed to determine a similarity score cutoff threshold. During inference, all chunks with similarity exceeding this threshold are retrieved to provide context to the LLM, ensuring the true answer is captured in the context with a (1-{\alpha}) confidence level. We provide a Python package that enables users to implement the entire workflow proposed in our work, only using LLMs and without human intervention., Comment: Github code: https://github.com/Mayo-Radiology-Informatics-Lab/conflare