Deep neural networks (DNN) has received increasing attention in machine learning applications in the last several years. Recently, a non-asymptotic error bound has been developed to measure the performance of the fully connected DNN estimator with ReLU ...

Problem statement

Machine Learning (ML) methods have been developed rapidly. Among different ML methods, Deep Neural Networks (DNN) received increased attention due to their great empirical performance. However, their theoretical foundation is ...

To address the barrier caused by the black-box nature of Deep Learning (DL) for practical deployment, eXplainable Artificial Intelligence (XAI) has emerged and is developing rapidly. While significant progress has been made in explanation techniques for ...

Web servers are the backbone of modern Internet infrastructure, serving as the primary medium for online information distribution. Despite their critical role, web servers are susceptible to cyber-attacks. While current firewall mechanisms provide some ...

Natural disasters, such as earthquakes, floods, fires, and hurricanes, result in extensive damage and challenge effective disaster management and rescue efforts. Timely detection of disaster zones and accurate crowd density estimation are essential for ...

Deep learning algorithms have advanced in medical imaging, and they have demonstrated promising outcomes in the diagnosis of numerous disorders. A recent study found that adversarial examples/attacks, which entail making minute, almost undetectable ...

Machine learning has become increasingly important in biomechanics. It allows to unveil hidden patterns from large and complex data, which leads to a more comprehensive understanding of biomechanical processes and deeper insights into human movement. ...

Distributed graph neural network (GNN) training facilitates learning on massive graphs that surpass the storage and computational capabilities of a single machine. Traditional distributed frameworks strive for performance parity with centralized training ...

Bindings for machine learning frameworks (such as TensorFlow and PyTorch) allow developers to integrate a framework’s functionality using a programming language different from the framework’s default language (usually Python). In this article, we study ...

Invisible watermarking can be used as an important tool for copyright certification in the Metaverse. However, with the advent of deep learning, Deep Neural Networks (DNNs) have posed new threats to this technique. For example, artificially trained DNNs ...

Link prediction in multilayer networks aims to predict missing links at the target layer by incorporating structural information from both auxiliary layers and the target layer. Existing methods tend to learn layer-specific knowledge to maximize the link ...

Decentralized finance (DeFi) represents a novel financial system but faces significant fraud challenges, leading to substantial losses. Recent advancements in artificial intelligence (AI) show potential for complex fraud detection. Despite growing ...

Tensor decomposition of convolutional and fully-connected layers is an effective way to reduce parameters and FLOP in neural networks. Due to memory and power consumption limitations of mobile or embedded devices, the quantization step is usually ...

Floor identification has gained much attention due to the increasing demand for indoor location-based services, especially prompt emergency response services. Leveraging cellular signals for floor identification has recently been of interest due to the ...

Message passing scheme is a general idea for graph neural networks (GNNs) to learn node representations. During message passing, given a target node, we transform and aggregate the feature vectors of its neighbours and generate a representation vector for ...

Sleep disorders, including conditions such as obstructive sleep apnea, significantly impact the quality of life and pose serious health risks. Early detection and diagnosis are crucial for effective management. This study explores various machine learning ...

Multi-label text classification (MLTC) is the task of assigning multiple relevant labels to a text, which is particularly challenging due to the complex interdependencies between labels and the imbalanced distribution of label frequencies. Domain-specific ...

Embeddings in deep neural networks are essential for processing high-dimensional and categorical data by converting it into compact, low-dimensional vectors. This conversion enables the model to capture complex semantic relationships and improves its ...

Rice is a crucial agricultural crop, but it is susceptible to various diseases. Although Convolutional Neural Networks (CNN) excel in classifying plant diseases, their significant computational demands render them impractical for resource-limited devices ...

Deepfake technology presents critical cybersecurity challenges that have become more popular since easily accessible applications have become more widely available. The proliferation of fake portrait videos constitutes a serious risk to the legal system, ...

Multi-Agent Reinforcement Learning (MARL) is susceptible to Adversarial Machine Learning (AML) attacks. Execution-time AML attacks against MARL are complex due to effects that propagate across time and between agents. To understand the interaction between ...