Yizhu Wen

ORCID: 0009-0008-0479-4991
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Big Data and Business Intelligence
  • Natural Language Processing Techniques
  • Topic Modeling
  • Adversarial Robustness in Machine Learning
  • Speech and dialogue systems
  • Neural Networks and Applications
  • Bayesian Methods and Mixture Models
  • Digital and Cyber Forensics
  • Explainable Artificial Intelligence (XAI)
  • Privacy-Preserving Technologies in Data
  • Ethics and Social Impacts of AI
  • Advanced Data Processing Techniques
  • Socioeconomic Development in MENA
  • Visual Attention and Saliency Detection
  • Language, Metaphor, and Cognition
  • Quantum and electron transport phenomena
  • Big Data and Digital Economy
  • Generative Adversarial Networks and Image Synthesis
  • Advanced Memory and Neural Computing
  • Data Quality and Management
  • Neural Networks and Reservoir Computing
  • Advanced Neural Network Applications
  • Network Security and Intrusion Detection
  • Artificial Intelligence in Healthcare and Education
  • Computational Physics and Python Applications

University of Hawaii System
2025

10.1109/icnc64010.2025.10993984 article EN 2016 International Conference on Computing, Networking and Communications (ICNC) 2025-02-17

10.1109/icme57554.2024.10687685 article EN 2022 IEEE International Conference on Multimedia and Expo (ICME) 2024-07-15

This book begins with a detailed introduction to the fundamental principles and historical development of GANs, contrasting them traditional generative models elucidating core adversarial mechanisms through illustrative Python examples. The text systematically addresses mathematical theoretical underpinnings including probability theory, statistics, game theory providing solid framework for understanding objectives, loss functions, optimisation challenges inherent GAN training. Subsequent...

10.48550/arxiv.2502.04116 preprint EN arXiv (Cornell University) 2025-02-06

Large Language Models (LLMs) have become a cornerstone of modern artificial intelligence (AI), finding applications across various domains such as healthcare, finance, entertainment, and customer service. To understand their ethical social implications, it is essential to first grasp what these models are, how they function, why carry significant impact. This introduction aims provide comprehensive beginner-friendly overview LLMs, introducing basic structure, training process, the types...

10.31219/osf.io/svwh9_v3 preprint EN 2025-04-16

This book presents a comprehensive exploration of GPGPU (General Purpose Graphics Processing Unit) and its applications in deep learning machine learning. It focuses on how parallel computing, particularly through the use CUDA (Compute Unified Device Architecture), can unlock unprecedented computational power for complex tasks. The provides detailed discussions CPU GPU architectures, data flow learning, advanced features like streams, concurrency, dynamic parallelism. Furthermore, it delves...

10.48550/arxiv.2410.05686 preprint EN arXiv (Cornell University) 2024-10-08

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond health-care, software engineering, conversational systems. Despite these advancements in the past few years, LLMs shown considerable vulnerabilities, particularly to prompt injection jailbreaking attacks. This review analyzes state of research on vulnerabilities presents available defense strategies. We roughly categorize...

10.31219/osf.io/z8jk3 preprint EN 2024-10-17

This book offers an in-depth exploration of object detection and semantic segmentation, combining theoretical foundations with practical applications. It covers state-of-the-art advancements in machine learning deep learning, a focus on convolutional neural networks (CNNs), YOLO architectures, transformer-based approaches like DETR. The also delves into the integration artificial intelligence (AI) techniques large language models for enhanced complex environments. A thorough discussion big...

10.48550/arxiv.2410.15584 preprint EN arXiv (Cornell University) 2024-10-20

Artificial Intelligence (AI) has permeated numerous aspects of our daily lives, from predictive text on smartphones to complex decision-making systems in healthcare and finance. While AI shown remarkable accuracy efficiency, it is often criticized for being a 'black box,' particularly when comes models like deep learning large language (LLMs). This where Explainable (XAI) into play.Explainable aims make decisions transparent, understandable, interpretable. The lack interpretability raised...

10.31219/osf.io/wbk36 preprint EN 2024-12-04

Explainable Artificial Intelligence (XAI) addresses the growing need for transparency and interpretability in AI systems, enabling trust accountability decision-making processes. This book offers a comprehensive guide to XAI, bridging foundational concepts with advanced methodologies. It explores traditional models such as Decision Trees, Linear Regression, Support Vector Machines, alongside challenges of explaining deep learning architectures like CNNs, RNNs, Large Language Models (LLMs),...

10.48550/arxiv.2412.00800 preprint EN arXiv (Cornell University) 2024-12-01

Tabular data plays a crucial role in various domains but often suffers from missing values, thereby curtailing its potential utility. Traditional imputation techniques frequently yield suboptimal results and impose substantial computational burdens, leading to inaccuracies subsequent modeling tasks. To address these challenges, we propose DiffImpute, novel Denoising Diffusion Probabilistic Model (DDPM). Specifically, DiffImpute is trained on complete tabular datasets, ensuring that it can...

10.48550/arxiv.2403.13863 preprint EN arXiv (Cornell University) 2024-03-20

Object-Oriented Programming (OOP) has become a crucial paradigm for managing the growing complexity of modern software systems, particularly in fields like machine learning, deep large language models (LLM), and data analytics. This work provides comprehensive introduction to integration OOP techniques within these domains, with focus on improving code modularity, maintainability, scalability. We begin by outlining evolution computing rise OOP, followed an in-depth discussion key principles...

10.48550/arxiv.2409.19916 preprint EN arXiv (Cornell University) 2024-09-29

This manuscript presents a comprehensive guide to Automated Machine Learning (AutoML), covering fundamental principles, practical implementations, and future trends. The paper is structured assist both beginners experienced practitioners, with detailed discussions on popular AutoML tools such as TPOT, AutoGluon, Auto-Keras. It also addresses emerging topics like Neural Architecture Search (NAS) AutoML's applications in deep learning. We believe this work will contribute ongoing research...

10.48550/arxiv.2410.09596 preprint EN arXiv (Cornell University) 2024-10-12

This article provides a detailed exploration of blockchain technology and its applications across various fields. It begins with an introduction to cryptography fundamentals, including symmetric asymmetric encryption, their roles in ensuring security trust within systems. The then delves into the structure mechanics Bitcoin Ethereum, covering topics such as proof-of-work, proof-of-stake, smart contracts. Additionally, it highlights practical industries like decentralized finance (DeFi),...

10.48550/arxiv.2410.10110 preprint EN arXiv (Cornell University) 2024-10-13

This book explores the role of Artificial Intelligence (AI), Machine Learning (ML), and Deep (DL) in driving progress big data analytics management. The focuses on simplifying complex mathematical concepts behind deep learning, offering intuitive visualizations practical case studies to help readers understand how neural networks technologies like Convolutional Neural Networks (CNNs) work. It introduces several classic models such as Transformers, GPT, ResNet, BERT, YOLO, highlighting their...

10.48550/arxiv.2409.17120 preprint EN arXiv (Cornell University) 2024-09-25

This book serves as an introduction to deep learning and machine learning, focusing on their applications in big data analytics. It covers essential concepts, tools like ChatGPT Claude, hardware recommendations, practical guidance setting up development environments using libraries PyTorch TensorFlow. Designed for beginners advanced users alike, it provides step-by-step instructions, hands-on projects, insights into AI's future, including AutoML edge computing.

10.48550/arxiv.2410.01268 preprint EN arXiv (Cornell University) 2024-10-02

This book, Design Patterns in Machine Learning and Deep Learning: Advancing Big Data Analytics Management, presents a comprehensive study of essential design patterns tailored for large-scale machine learning deep applications. The book explores the application classical software engineering patterns, Creational, Structural, Behavioral, Concurrency Patterns, to optimize development, maintenance, scalability big data analytics systems. Through practical examples detailed Python...

10.48550/arxiv.2410.03795 preprint EN arXiv (Cornell University) 2024-10-03

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, conversational systems. Despite these advancements in the past few years, LLMs shown considerable vulnerabilities, particularly to prompt injection jailbreaking attacks. This review analyzes state of research on vulnerabilities presents available defense strategies. We roughly categorize...

10.48550/arxiv.2410.15236 preprint EN arXiv (Cornell University) 2024-10-19

Advancements in artificial intelligence, machine learning, and deep learning have catalyzed the transformation of big data analytics management into pivotal domains for research application. This work explores theoretical foundations, methodological advancements, practical implementations these technologies, emphasizing their role uncovering actionable insights from massive, high-dimensional datasets. The study presents a systematic overview preprocessing techniques, including cleaning,...

10.48550/arxiv.2412.02187 preprint EN arXiv (Cornell University) 2024-12-03
Coming Soon ...