Kirjojen hintavertailu. Mukana 11 244 527 kirjaa ja 12 kauppaa.

Kirjahaku

Etsi kirjoja tekijän nimen, kirjan nimen tai ISBN:n perusteella.

1000 tulosta hakusanalla Pin-Yu Chen; Cho-Jui Hsieh

Adversarial Robustness for Machine Learning

Adversarial Robustness for Machine Learning

Pin-Yu Chen; Cho-Jui Hsieh

ELSEVIER SCIENCE PUBLISHING CO INC
2022
nidottu
Adversarial Robustness for Machine Learning summarizes the recent progress on this topic and introduces popular algorithms on adversarial attack, defense and veri?cation. Sections cover adversarial attack, veri?cation and defense, mainly focusing on image classi?cation applications which are the standard benchmark considered in the adversarial robustness community. Other sections discuss adversarial examples beyond image classification, other threat models beyond testing time attack, and applications on adversarial robustness. For researchers, this book provides a thorough literature review that summarizes latest progress in the area, which can be a good reference for conducting future research. In addition, the book can also be used as a textbook for graduate courses on adversarial robustness or trustworthy machine learning. While machine learning (ML) algorithms have achieved remarkable performance in many applications, recent studies have demonstrated their lack of robustness against adversarial disturbance. The lack of robustness brings security concerns in ML models for real applications such as self-driving cars, robotics controls and healthcare systems.
Introduction to Foundation Models

Introduction to Foundation Models

Pin-Yu Chen; Sijia Liu

Springer International Publishing AG
2025
sidottu
This book offers an extensive exploration of foundation models, guiding readers through the essential concepts and advanced topics that define this rapidly evolving research area. Designed for those seeking to deepen their understanding and contribute to the development of safer and more trustworthy AI technologies, the book is divided into three parts providing the fundamentals, advanced topics in foundation modes, and safety and trust in foundation models: Part I introduces the core principles of foundation models and generative AI, presents the technical background of neural networks, delves into the learning and generalization of transformers, and finishes with the intricacies of transformers and in-context learning. Part II introduces automated visual prompting techniques, prompting LLMs with privacy, memory-efficient fine-tuning methods, and shows how LLMs can be reprogrammed for time-series machine learning tasks. It explores how LLMs can be reused for speech tasks, how synthetic datasets can be used to benchmark foundation models, and elucidates machine unlearning for foundation models. Part III provides a comprehensive evaluation of the trustworthiness of LLMs, introduces jailbreak attacks and defenses for LLMs, presents safety risks when find-tuning LLMs, introduces watermarking techniques for LLMs, presents robust detection of AI-generated text, elucidates backdoor risks in diffusion models, and presents red-teaming methods for diffusion models. Mathematical notations are clearly defined and explained throughout, making this book an invaluable resource for both newcomers and seasoned researchers in the field.
A Fool's Success Story - A Memoir By Dr. Pin Yu Chang
Preface: Dr. P.Y. Chang Always Ahead of Others Forty years ago, I already heard about the famous P. Y. Chang. At that time I was working and struggling to make a living, but Dr. Chang was already a well-known millionaire in the Washington, D. C. area. People called him millionaire Chang. I was very curious about him. My late wife Rowena Fu and Mrs. Frances Chang were both members of the Tunghsin Choral Society. One time we were invited to his home. That's how I got to know him. I found out that unlike the rich Chinese, who live in mansions and drive expensive cars, they were just like the ordinary Chinese having a simple home and leading a simple life. This whetted my curiosity even more, and my respect for him welled up in my heart. Chinese intellectuals have the mentality that "all other pursuits are worthless, only the study of books ranks first and foremost." They consider money stinking. As a result, they loathe labor, and live their poor but principled life. They consider themselves high-minded, or they join the bureaucracy and become dependents of the power elites. If they are clean and not corrupt, when they lose their official jobs, they don't have the means to be independent financially. According to Western sinologists, this is the reason why China's intelligentsia has never been a counterbalancing force to the ruling class. P. Y. Chang is different from traditional Chinese intellectuals. He advocates that "if you don't seek fame and profit, you must be mediocre." He also says that "to die of poverty is criminal." He's certainly an avantgarde against traditional thinking. He is the one that introduces this new thinking and brings some fresh air. Hence, when he worked in U. S. agencies and companies, he insisted on his right to have a side line. His advice to the talented men and women: You must know how to manage money and make money. His contrarian way of thinking and behavior demands special attention. As a matter of fact, the standard by which the Americans judge a person's success or failure is usually his wealth. The way to create wealth in America is by way of one's intelligence and wisdom, billionaires like Bill Gates of Microsoft, Steve Jobs of Apple and Mark Zuckerberg of Facebook are all like that. That's why the Americans attach great importance to intellectual property rights. The Chinese never had such a concept. When he was 70, his relatives and friends threw a birthday party in his honor. I was invited to make a short speech on that occasion. In my remarks I cited a poem by a famous general and strategist Cao Cao (曹操) of the Eastern Han dynasty. The poem written by Cao Cao in his twilight years reads in part: "Like an old horse transporting a heavy load of timber, my destination is hundreds of miles away." I wished P. Y. Chang just like that horse with a long journey ahead. When it was P. Y's turn to respond, he quoted the American expression, " I'll go the extra mile for the rest of my life." Chinese and American diction, a perfect union, his witticism showed itself brilliantly and he got a round of applause. I have nothing but admiration for him. To this day, I can't forget that remarkable evening. More than a decade has since passed, P. Y. Chang is still in excellent health, old but vigorous. He has gone not just the extra mile, but thousands of miles. No wonder he is always ahead of others. We look up to him and follow him forever. Norman Fu, former U. S. Bureau Chief of The China Times
Isotropic and Anisotropic Seismic Tomography Using Active Source and Earthquake Records
This book presents investigations on the Earth's seismic structure using both active-source and natural earthquake records. It discusses the ground-truth data obtained from the TAiwan Integrated GEodynamics Research (TAIGER) active-source experiments that provides excellent and unique insights into the shallow crustal structures beneath Taiwan. It also explores the full-wave sensitivity kernels, which account for the effects of all possible wave interferences involved in shear-wave splitting and therefore loosen the restrictions on source-receiver geometry amenable to shear-wave splitting analysis. Moreover, it describes the 3D Fréchet kernels, which enable us to resolve the vertical and lateral variations in seismic anisotropy and obtain 3D images of the Earth's anisotropic structure, as well as the practice in Southern California that enables us to infer the state of the stress and strain in the lithosphere and the dynamics of the asthenospheric mantle flow for a better understanding of the strength and deformation in the upper mantle beneath the San Andreas Fault system.
Isotropic and Anisotropic Seismic Tomography Using Active Source and Earthquake Records
This book presents investigations on the Earth's seismic structure using both active-source and natural earthquake records. It discusses the ground-truth data obtained from the TAiwan Integrated GEodynamics Research (TAIGER) active-source experiments that provides excellent and unique insights into the shallow crustal structures beneath Taiwan. It also explores the full-wave sensitivity kernels, which account for the effects of all possible wave interferences involved in shear-wave splitting and therefore loosen the restrictions on source-receiver geometry amenable to shear-wave splitting analysis. Moreover, it describes the 3D Fréchet kernels, which enable us to resolve the vertical and lateral variations in seismic anisotropy and obtain 3D images of the Earth's anisotropic structure, as well as the practice in Southern California that enables us to infer the state of the stress and strain in the lithosphere and the dynamics of the asthenospheric mantle flow for a better understanding of the strength and deformation in the upper mantle beneath the San Andreas Fault system.
Mathematical Principle and Fractal Analysis of Mesoscale Eddy

Mathematical Principle and Fractal Analysis of Mesoscale Eddy

Shu-Tang Liu; Yu-Pin Wang; Zhi-Min Bi; Yin Wang

Springer Verlag, Singapore
2021
sidottu
This book focuses on universal nonlinear dynamics model of mesoscale eddies. The results of this book are not only the direct-type applications of pure mathematical limit cycle theory and fractal theory in practice but also the classic combination of nonlinear dynamic systems in mathematics and the physical oceanography. The universal model and experimental verification not only verify the relevant results that are obtained by Euler's form but also, more importantly, are consistent with observational numerical statistics. Due to the universality of the model, the consequences of the system are richer and more complete. The comprehensive and systematic mathematical modeling of mesoscale eddies is one of the major features of the book, which is particularly suited for readers who are interested to learn fractal analysis and prediction in physical oceanography. The book benefits researchers, engineers, and graduate students in the fields of mesoscale eddies, fractal, chaos, and other applications, etc.
Mathematical Principle and Fractal Analysis of Mesoscale Eddy

Mathematical Principle and Fractal Analysis of Mesoscale Eddy

Shu-Tang Liu; Yu-Pin Wang; Zhi-Min Bi; Yin Wang

SPRINGER VERLAG, SINGAPORE
2022
nidottu
This book focuses on universal nonlinear dynamics model of mesoscale eddies. The results of this book are not only the direct-type applications of pure mathematical limit cycle theory and fractal theory in practice but also the classic combination of nonlinear dynamic systems in mathematics and the physical oceanography. The universal model and experimental verification not only verify the relevant results that are obtained by Euler's form but also, more importantly, are consistent with observational numerical statistics. Due to the universality of the model, the consequences of the system are richer and more complete. The comprehensive and systematic mathematical modeling of mesoscale eddies is one of the major features of the book, which is particularly suited for readers who are interested to learn fractal analysis and prediction in physical oceanography. The book benefits researchers, engineers, and graduate students in the fields of mesoscale eddies, fractal, chaos, and other applications, etc.