Search

Representational analysis explores how input data of a neural system are encoded in high dimensional spaces of its distributed neural activations, and how we can compare different systems, for instance, artificial neural networks and brains, on those grounds. While existing methods offer important insights, they typically do not account for local intrinsic geometrical properties within the high-dimensional representation spaces. To go beyond these limitations, we explore Ollivier-Ricci curvature and Ricci flow as tools to study the alignment of representations between humans and artificial neural systems on a geometric level. As a proof-of-principle study, we compared the representations of face stimuli between VGG-Face, a human-aligned version of VGG-Face, and corresponding human similarity judgments from a large online study. Using this discrete geometric framework, we were able to identify local structural similarities and differences by examining the distributions of node and edge curvature and higher-level properties by detecting and comparing community structure in the representational graphs., Comment: Presented at NeuReps workshop, NeurIPS 2024

Machine learning (ML) models frequently rely on training data that may include sensitive or personal information, raising substantial privacy concerns. Legislative frameworks such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA) have necessitated the development of strategies that preserve privacy while maintaining the utility of data. In this paper, we investigate the capability of Large Language Models (LLMs) to generate synthetic datasets integrated with Differential Privacy (DP) mechanisms, thereby enabling data-driven research and model training without direct exposure of sensitive information. Our approach incorporates DP-based noise injection methods, including Laplace and Gaussian distributions, into the data generation process. We then evaluate the utility of these DP-enhanced synthetic datasets by comparing the performance of ML models trained on them against models trained on the original data. To substantiate privacy guarantees, we assess the resilience of the generated synthetic data to membership inference attacks and related threats. The experimental results demonstrate that integrating DP within LLM-driven synthetic data generation offers a viable balance between privacy protection and data utility. This study provides a foundational methodology and insight into the privacy-preserving capabilities of LLMs, paving the way for compliant and effective ML research and applications., Comment: 15 pages, 1 figure, 5 tables

This paper explores and enhances the application of Transfer Learning (TL) for multilabel image classification in medical imaging, focusing on brain tumor class and diabetic retinopathy stage detection. The effectiveness of TL-using pre-trained models on the ImageNet dataset-varies due to domain-specific challenges. We evaluate five pre-trained models-MobileNet, Xception, InceptionV3, ResNet50, and DenseNet201-on two datasets: Brain Tumor MRI and APTOS 2019. Our results show that TL models excel in brain tumor classification, achieving near-optimal metrics. However, performance in diabetic retinopathy detection is hindered by class imbalance. To mitigate this, we integrate the Synthetic Minority Over-sampling Technique (SMOTE) with TL and traditional machine learning(ML) methods, which improves accuracy by 1.97%, recall (sensitivity) by 5.43%, and specificity by 0.72%. These findings underscore the need for combining TL with resampling techniques and ML methods to address data imbalance and enhance classification performance, offering a pathway to more accurate and reliable medical image analysis and improved patient outcomes with minimal extra computation powers., Comment: Accepted in 27th International Conference on Computer and Information Technology (ICCIT) 2024

The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages and varied cultural contexts, largely due to a lack of high-quality, diverse, and safety-vetted data. Consequently, these models often struggle to understand low-resource languages and cultural nuances in a manner free from toxicity. To address these limitations, we introduce Maya, an open-source Multimodal Multilingual model. Our contributions are threefold: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; 2) a thorough analysis of toxicity within the LLaVA dataset, followed by the creation of a novel toxicity-free version across eight languages; and 3) a multilingual image-text model supporting these languages, enhancing cultural and linguistic comprehension in vision-language tasks. Code available at https://github.com/nahidalam/maya.

Anti-Muslim hate speech has emerged within memes, characterized by context-dependent and rhetorical messages using text and images that seemingly mimic humor but convey Islamophobic sentiments. This work presents a novel dataset and proposes a classifier based on the Vision-and-Language Transformer (ViLT) specifically tailored to identify anti-Muslim hate within memes by integrating both visual and textual representations. Our model leverages joint modal embeddings between meme images and incorporated text to capture nuanced Islamophobic narratives that are unique to meme culture, providing both high detection accuracy and interoperability., Comment: Accepted (Poster) - NeurIPS 2024 Workshop MusIML

Strong lensing directly probes the internal structure of the lensing galaxies. In this paper, we investigate the relation between the internal structure of massive elliptical galaxies and their environment using a sample of 15 strong lensing systems. We performed lens modeling for them using Lenstronomy and constrained the mass and light distributions of the deflector galaxies. We adopt the local galaxy density as a metric for the environment and test our results against several alternative definitions of it. We robustly find that the centroid offset between the mass and light is not correlated with the local galaxy density. This result supports using centroid offsets as a probe of dark matter theories since the environment's impact on it can be treated as negligible. Although we find a strong correlation between the position angle offset and the standard definition of the local galaxy density, consistent with previous studies, the correlation becomes weaker for alternative definitions of the local galaxy density. This result weakens the support for interpreting the position angle misalignment as having originated from interaction with the environment. Furthermore, we find the 'residual shear' magnitude in the lens model to be uncorrelated with the local galaxy density, supporting the interpretation of the residual shear originating, in part, from the inadequacy in modeling the angular structure of the lensing galaxy and not solely from the structures present in the environment or along the line of sight., Comment: 15 pages, 9 figures, 3 tables. Submitted to A&A

People's cooperation in adopting protective measures is effective in epidemic control and creates herd immunity as a public good. Similarly, the presence of an epidemic is a driving factor for the formation and improvement of cooperation. Here, we study the coevolution of epidemic dynamics and the public good game as a paradigm of cooperation dynamics. Using simulations and a mean-field description, we show that the presence of an epidemic can promote cooperation even in regimes where cooperation would not naturally emerge in the standard public good game. The coupling of the two dynamics leads to a rich phenomenology, such as the more efficient control of epidemics, instead of higher cooperation, when the economic benefit of cooperation increases, or higher cooperation, but not higher disease spread, when disease transmission probability increases. Besides, our work shows that a higher altruistic effect of cooperation in controlling the disease can only be detrimental to the evolution of cooperation and disease control. Rather, individuals' choices in adopting costly preventive measures are predominantly driven by the self-interested effect of such measures in reducing the probability of getting infected., Comment: 8 pages, 8 figures

We study an extension to directed graphs of the parameter called the $b$-chromatic number of a graph in terms of acyclic vertex colorings: the dib-chromatic number. We give general bounds for this parameter. We also show some results about tournaments and regular digraphs., Comment: 10 pages, 1 figure

This paper addresses the optimal control of quantum coherence in multi-level systems, modeled by the Lindblad master equation, which captures both unitary evolution and environmental dissipation. We develop an energy minimization framework to control the evolution of a qutrit (three-level) quantum system while preserving coherence between states. The control problem is formulated using Pontryagin's Minimum Principle in the form of Gamkrelidze, incorporating state constraints to ensure coherence remains within desired bounds. Our approach accounts for Markovian decoherence, demonstrating that the Lindblad operator is non-unital, which reflects the irreversible decay processes inherent in the system. The results provide insights into effectively maintaining quantum coherence in the presence of dissipation., Comment: 8 pages, 4 figures

We investigate the effect of a constant static bias force on the dynamically induced shape morphing of a pre-buckled bistable beam, focusing on the beam's ability to change its vibration to be near different stable states under harmonic excitation. Our study explores four categories of oscillatory motions: switching, reverting, vacillating, and intra-well in the parameter space. We aim to achieve transitions between stable states of the pre-buckled bistable beam with minimal excitation amplitude. Our findings demonstrate the synergistic effects between dynamic excitation and static bias force, showing a broadening of the non-fractal region for switching behavior (i.e., switching from the first stable state to the second stable state) in the parameter space. This study advances the understanding of the dynamics of key structural components for multi-stable mechanical metamaterials, offering new possibilities for novel designs in adaptive applications.

Navigating large-scale outdoor environments requires complex reasoning in terms of geometric structures, environmental semantics, and terrain characteristics, which are typically captured by onboard sensors such as LiDAR and cameras. While current mobile robots can navigate such environments using pre-defined, high-precision maps based on hand-crafted rules catered for the specific environment, they lack commonsense reasoning capabilities that most humans possess when navigating unknown outdoor spaces. To address this gap, we introduce the Global Navigation Dataset (GND), a large-scale dataset that integrates multi-modal sensory data, including 3D LiDAR point clouds and RGB and 360-degree images, as well as multi-category traversability maps (pedestrian walkways, vehicle roadways, stairs, off-road terrain, and obstacles) from ten university campuses. These environments encompass a variety of parks, urban settings, elevation changes, and campus layouts of different scales. The dataset covers approximately 2.7km2 and includes at least 350 buildings in total. We also present a set of novel applications of GND to showcase its utility to enable global robot navigation, such as map-based global navigation, mapless navigation, and global place recognition.

Since the publication of CLIP, the approach of using InfoNCE loss for contrastive pre-training has become widely popular for bridging two or more modalities. Despite its wide adoption, CLIP's original design choices of L2 normalization and cosine similarity logit have rarely been revisited. We have systematically experimented with alternative geometries and softmax logits for language-image pre-training and identified that variants with intuitive Euclidean geometry, Euclidean CLIP (EuCLIP), match or exceed the performance of CLIP and support hierarchical relationships at least as well as more complicated hyperbolic alternative., Comment: ECCV 2024 - Beyond Euclidean Workshop

This study presents an advanced approach to lumbar spine segmentation using deep learning techniques, focusing on addressing key challenges such as class imbalance and data preprocessing. Magnetic resonance imaging (MRI) scans of patients with low back pain are meticulously preprocessed to accurately represent three critical classes: vertebrae, spinal canal, and intervertebral discs (IVDs). By rectifying class inconsistencies in the data preprocessing stage, the fidelity of the training data is ensured. The modified U-Net model incorporates innovative architectural enhancements, including an upsample block with leaky Rectified Linear Units (ReLU) and Glorot uniform initializer, to mitigate common issues such as the dying ReLU problem and improve stability during training. Introducing a custom combined loss function effectively tackles class imbalance, significantly improving segmentation accuracy. Evaluation using a comprehensive suite of metrics showcases the superior performance of this approach, outperforming existing methods and advancing the current techniques in lumbar spine segmentation. These findings hold significant advancements for enhanced lumbar spine MRI and segmentation diagnostic accuracy.

The popularity of the Internet of Things (IoT) has driven its usage in our homes and industries over the past 10-12 years. However, there have been some major issues related to identity management and ownership transfer involving IoT devices, particularly for consumer IoT devices, e. g. smart appliances such as smart TVs, smart refrigerators, and so on. There have been a few attempts to address this issue; however, user-centric and effective ownership and identity management of IoT devices have not been very successful so far. Recently, blockchain technology has been used to address these issues with limited success. This article presents a Self-sovereign Identity (SSI) based system that facilitates a secure and user-centric ownership management and transfer of consumer IoT devices. The system leverages a number of emerging technologies, such as blockchain and decentralized identifiers (DID), verifiable credentials (VC), under the umbrella of SSI. We present the architecture of the system based on a threat model and requirement analysis, discuss the implementation of a Proof-of-Concept based on the proposed system and illustrate a number of use-cases with their detailed protocol flows. Furthermore, we analyse its security using ProVerif, a state-of-the art protocol verification tool and examine its performance.

Cancer is a highly heterogeneous disease with significant variability in molecular features and clinical outcomes, making diagnosis and treatment challenging. In recent years, high-throughput omic technologies have facilitated the discovery of mechanisms underlying various cancer subtypes by providing diverse omics data, such as gene expression, DNA methylation, and miRNA expression. However, the complexity and heterogeneity of multi-omics data present significant challenges for their integration in exploring cancer subtypes. Various methods have been proposed to address these challenges. In this paper, we propose a novel and straightforward approach for identifying cancer subtypes by integrating patient-specific subnetworks features from different omics data. We construct patient-specific induced subnetwork using a random walk with restart algorithm from patient similarity networks (PSNs) and compute nine structural properties that capture essential network topology. These features are integrated across the three omic datasets to form comprehensive patient profiles. K-means clustering is then applied for cancer subtype identification. We evaluate our approach on five cancer datasets, including breast invasive carcinoma, colon adenocarcinoma, glioblastoma multiforme, kidney renal clear cell carcinoma, and lung squamous cell carcinoma, for three different omic data types. The evaluation shows that our method produces promising and effective results, demonstrating competitive or superior performance compared to existing methods and underscoring its potential for advancing personalized cancer diagnosis and treatment., Comment: 12, 3

The increasing prevalence of graph-structured data across various domains has intensified greater interest in graph classification tasks. While numerous sophisticated graph learning methods have emerged, their complexity often hinders practical implementation. In this article, we address this challenge by proposing a method that constructs feature vectors based on fundamental graph structural properties. We demonstrate that these features, despite their simplicity, are powerful enough to capture the intrinsic characteristics of graphs within the same class. We explore the efficacy of our approach using three distinct machine learning methods, highlighting how our feature-based classification leverages the inherent structural similarities of graphs within the same class to achieve accurate classification. A key advantage of our approach is its simplicity, which makes it accessible and adaptable to a broad range of applications, including social network analysis, bioinformatics, and cybersecurity. Furthermore, we conduct extensive experiments to validate the performance of our method, showing that it not only reveals a competitive performance but in some cases surpasses the accuracy of more complex, state-of-the-art techniques. Our findings suggest that a focus on fundamental graph features can provide a robust and efficient alternative for graph classification, offering significant potential for both research and practical applications., Comment: 25 pages, 6 Figures

Learned image compression (LIC) is currently the cutting-edge method. However, the inherent difference between testing and training images of LIC results in performance degradation to some extent. Especially for out-of-sample, out-of-distribution, or out-of-domain testing images, the performance of LIC dramatically degraded. Classical LIC is a serial image compression (SIC) approach that utilizes an open-loop architecture with serial encoding and decoding units. Nevertheless, according to the theory of automatic control, a closed-loop architecture holds the potential to improve the dynamic and static performance of LIC. Therefore, a circular image compression (CIC) approach with closed-loop encoding and decoding elements is proposed to minimize the gap between testing and training images and upgrade the capability of LIC. The proposed CIC establishes a nonlinear loop equation and proves that steady-state error between reconstructed and original images is close to zero by Taylor series expansion. The proposed CIC method possesses the property of Post-Training and plug-and-play which can be built on any existing advanced SIC methods. Experimental results on five public image compression datasets demonstrate that the proposed CIC outperforms five competing state-of-the-art open-source SIC algorithms in reconstruction capacity. Experimental results further show that the proposed method is suitable for out-of-sample testing images with dark backgrounds, sharp edges, high contrast, grid shapes, or complex patterns.

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in parsing textual data and generating code. However, their performance in tasks involving tabular data, especially those requiring symbolic reasoning, faces challenges due to the structural variance and inconsistency in table cell values often found in web tables. In this paper, we introduce NormTab, a novel framework aimed at enhancing the symbolic reasoning performance of LLMs by normalizing web tables. We study table normalization as a stand-alone, one-time preprocessing step using LLMs to support symbolic reasoning on tabular data. Our experimental evaluation, conducted on challenging web table datasets such as WikiTableQuestion and TabFact, demonstrates that leveraging NormTab significantly improves symbolic reasoning performance, showcasing the importance and effectiveness of web table normalization for enhancing LLM-based symbolic reasoning tasks., Comment: Work in Progress

Viruses are submicroscopic agents that can infect all kinds of lifeforms and use their hosts' living cells to replicate themselves. Despite having some of the simplest genetic structures among all living beings, viruses are highly adaptable, resilient, and given the right conditions, are capable of causing unforeseen complications in their hosts' bodies. Due to their multiple transmission pathways, high contagion rate, and lethality, viruses are the biggest biological threat faced by animal and plant species. It is often challenging to promptly detect the presence of a virus in a possible host's body and accurately determine its type using manual examination techniques; however, it can be done using computer-based automatic diagnosis methods. Most notably, the analysis of Transmission Electron Microscopy (TEM) images has been proven to be quite successful in instant virus identification. Using TEM images collected from a recently published dataset, this article proposes a deep learning-based classification model to identify the type of virus within those images correctly. The methodology of this study includes two coherent image processing techniques to reduce the noise present in the raw microscopy images. Experimental results show that it can differentiate among the 14 types of viruses present in the dataset with a maximum of 97.44% classification accuracy and F1-score, which asserts the effectiveness and reliability of the proposed method. Implementing this scheme will impart a fast and dependable way of virus identification subsidiary to the thorough diagnostic procedures.

The Internet of Things (IoT) is expanding rapidly, which has created a need for sophisticated computational frameworks that can handle the data and security requirements inherent in modern IoT applications. However, traditional cloud computing frameworks have struggled with latency, scalability, and security vulnerabilities. Quantum-Edge Cloud Computing (QECC) is a new paradigm that effectively addresses these challenges by combining the computational power of quantum computing, the low-latency benefits of edge computing, and the scalable resources of cloud computing. This study has been conducted based on a published literature review, performance improvements, and metrics data from Bangladesh on smart city infrastructure, healthcare monitoring, and the industrial IoT sector. We have discussed the integration of quantum cryptography to enhance data integrity, the role of edge computing in reducing response times, and how cloud computing's resource abundance can support large IoT networks. We examine case studies, such as the use of quantum sensors in self-driving vehicles, to illustrate the real-world impact of QECC. Furthermore, the paper identifies future research directions, including developing quantum-resistant encryption and optimizing quantum algorithms for edge computing. The convergence of these technologies in QECC promises to overcome the existing limitations of IoT frameworks and set a new standard for the future of IoT applications.

In this paper, we study operator mean inequalities for the weighted arithmetic, geometric and harmonic means. We give a slight modification of Audenaert's result to show the relation between Kwong functions and operator monotone functions. Operator mean inequalities provide some analogs of the geometric concavity property for Kwong functions, operator convex, and operator monotone functions. Moreover, we give our points across by way of some examples which show the usage of our main results., Comment: Accepted by Arch. Math. (Basel)

In this paper, we obtain the subadditivity inequality of strongly operator convex functions on $(0, \infty)$ and $(-\infty,0)$. Applying the properties of operator convex functions, we deduce the subadditivity property of operator monotone functions on $(0, \infty)$. We give new operator inequalities involving strongly operator convex functions on an interval and the weighted operator means. We also investigate relations between strongly operator convex functions and Kwong functions on $(0, \infty)$. Moreover, we study the strongly operator convex functions on $(a, \infty)$ with $a>-\infty$ and also on left half line $(-\infty,b)$ with $b< \infty$. We show that any non-constant strongly operator convex function on $(a, \infty)$ is strictly operator decreasing, and any non-constant strongly operator convex function on $(-\infty,b)$ is strictly operator monotone. Consequently, if $g$ is a strongly operator convex function on $(a, \infty)$ or $(-\infty,b)$, we estimate lower bounds of $|g(A)-g(B)|$ whenever $A-B>0$., Comment: 15 pages

Lead halide perovskites have emerged as platforms for exciton-polaritonic studies at room temperature thanks to their excellent photoluminescence efficiency and synthetic versatility. In this work we find proof of strong exciton-photon coupling in cavities formed by the layered crystals themselves, a phenomenon known as self-hybridization effect. We use multi-layers of high quality Ruddlesden-Popper perovskites in their 2D crystalline form, benefitting from their quantum-well excitonic resonances and the strong Fabry-Perot cavity modes resulting from the total-internal-reflection at their smooth surfaces. Optical spectroscopy reveals bending of the cavity modes typical for exciton-polariton formation, and photoluminescence spectroscopy shows thickness dependent splitting of the excitonic resonance. Strikingly, local optical excitation with energy below the excitonic resonance of the flakes in photoluminescence measurements unveils coupling of light to in-plane polaritonic modes with directed propagation. These exciton-polaritons exhibit high coupling efficiencies and extremely low loss propagation mechanisms which is confirmed by finite difference time domain simulations. We therefore prove that mesoscopic 2D Ruddlesden-Popper perovskites flakes represent an effective but simple system to study the rich physics of exciton-polaritons at room temperature.