Practicing Trustworthy Machine Learning PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download Practicing Trustworthy Machine Learning PDF full book. Access full book title Practicing Trustworthy Machine Learning by Yada Pruksachatkun. Download full books in PDF and EPUB format.
Author: Yada Pruksachatkun Publisher: "O'Reilly Media, Inc." ISBN: 109812023X Category : Computers Languages : en Pages : 304
Book Description
With the increasing use of AI in high-stakes domains such as medicine, law, and defense, organizations spend a lot of time and money to make ML models trustworthy. Many books on the subject offer deep dives into theories and concepts. This guide provides a practical starting point to help development teams produce models that are secure, more robust, less biased, and more explainable. Authors Yada Pruksachatkun, Matthew McAteer, and Subhabrata Majumdar translate best practices in the academic literature for curating datasets and building models into a blueprint for building industry-grade trusted ML systems. With this book, engineers and data scientists will gain a much-needed foundation for releasing trustworthy ML applications into a noisy, messy, and often hostile world. You'll learn: Methods to explain ML models and their outputs to stakeholders How to recognize and fix fairness concerns and privacy leaks in an ML pipeline How to develop ML systems that are robust and secure against malicious attacks Important systemic considerations, like how to manage trust debt and which ML obstacles require human intervention
Author: Yada Pruksachatkun Publisher: "O'Reilly Media, Inc." ISBN: 109812023X Category : Computers Languages : en Pages : 304
Book Description
With the increasing use of AI in high-stakes domains such as medicine, law, and defense, organizations spend a lot of time and money to make ML models trustworthy. Many books on the subject offer deep dives into theories and concepts. This guide provides a practical starting point to help development teams produce models that are secure, more robust, less biased, and more explainable. Authors Yada Pruksachatkun, Matthew McAteer, and Subhabrata Majumdar translate best practices in the academic literature for curating datasets and building models into a blueprint for building industry-grade trusted ML systems. With this book, engineers and data scientists will gain a much-needed foundation for releasing trustworthy ML applications into a noisy, messy, and often hostile world. You'll learn: Methods to explain ML models and their outputs to stakeholders How to recognize and fix fairness concerns and privacy leaks in an ML pipeline How to develop ML systems that are robust and secure against malicious attacks Important systemic considerations, like how to manage trust debt and which ML obstacles require human intervention
Author: Yada Pruksachatkun Publisher: "O'Reilly Media, Inc." ISBN: 1098120248 Category : Computers Languages : en Pages : 303
Book Description
With the increasing use of AI in high-stakes domains such as medicine, law, and defense, organizations spend a lot of time and money to make ML models trustworthy. Many books on the subject offer deep dives into theories and concepts. This guide provides a practical starting point to help development teams produce models that are secure, more robust, less biased, and more explainable. Authors Yada Pruksachatkun, Matthew McAteer, and Subhabrata Majumdar translate best practices in the academic literature for curating datasets and building models into a blueprint for building industry-grade trusted ML systems. With this book, engineers and data scientists will gain a much-needed foundation for releasing trustworthy ML applications into a noisy, messy, and often hostile world. You'll learn: Methods to explain ML models and their outputs to stakeholders How to recognize and fix fairness concerns and privacy leaks in an ML pipeline How to develop ML systems that are robust and secure against malicious attacks Important systemic considerations, like how to manage trust debt and which ML obstacles require human intervention
Author: Lam M. Nguyen Publisher: Elsevier ISBN: 0443190380 Category : Computers Languages : en Pages : 436
Book Description
Federated Learning: Theory and Practice provides a holistic treatment to federated learning, starting with a broad overview on federated learning as a distributed learning system with various forms of decentralized data and features. A detailed exposition then follows of core challenges and practical modeling techniques and solutions, spanning a variety of aspects in communication efficiency, theoretical convergence and security, viewed from different perspectives. Part II features emerging challenges stemming from many socially driven concerns of federated learning as a future public machine learning service, and Part III and IV present a wide array of industrial applications of federated learning, including potential venues and visions for federated learning in the near future. This book provides a comprehensive and accessible introduction to federated learning which is suitable for researchers and students in academia and industrial practitioners who seek to leverage the latest advances in machine learning for their entrepreneurial endeavors Presents the fundamentals and a survey of key developments in the field of federated learning Provides emerging, state-of-the art topics that build on fundamentals Contains industry applications Gives an overview of visions of the future
Author: Thai Quang Le Publisher: ISBN: Category : Languages : en Pages : 0
Book Description
Trustworthy machine learning models are ones that not only have high accuracy but also well perform under various realistic constraints, security threats, and are transparent to users. By satisfying these constraints, machine learning models can gain trust from their users and thus make it easier for them to be adopted in practice. This thesis makes contributions on three aspects of trustworthy machine learning, namely (i) learning under uncertainty--i.e., able to learn with limited and/or noisy data, (ii) transparent to the end-users--i.e., being explainable to the end-users, and (iii) secured and resilient machine learning--i.e., adversarial attacks and defense from/against malicious actors. Particularly, this thesis proposes to overcome the lack of high-quality labeled textual data that is necessary for training effective ML classification models by directly synthesizing them in the data space using generative neural networks. Moreover, this thesis designs a novel algorithm that facilitates accurate and effective post-hoc explanations of neural networks' predictions to the end-users. Furthermore, this thesis also demonstrates the vulnerability of a wide range of fake news detection models in the literature against a carefully designed adversarial attack mechanism where the attackers can promote fake news or demote real news on social media via social discourse. This thesis also proposes a novel approach that adapts the "honeypot" concept from cybersecurity to proactively defend against a strong universal trigger attack. Last but not least, this thesis contributes to the adversarial text literature by proposing to study, extract and utilize not machine-generated but realistic human-written perturbations online. Through these technical contributions, this thesis hopes to advance the adoption of ML systems in high-stakes fields where mutual trust between humans and machines is paramount.
Author: Beena Ammanath Publisher: John Wiley & Sons ISBN: 1119867959 Category : Computers Languages : en Pages : 230
Book Description
An essential resource on artificial intelligence ethics for business leaders In Trustworthy AI, award-winning executive Beena Ammanath offers a practical approach for enterprise leaders to manage business risk in a world where AI is everywhere by understanding the qualities of trustworthy AI and the essential considerations for its ethical use within the organization and in the marketplace. The author draws from her extensive experience across different industries and sectors in data, analytics and AI, the latest research and case studies, and the pressing questions and concerns business leaders have about the ethics of AI. Filled with deep insights and actionable steps for enabling trust across the entire AI lifecycle, the book presents: In-depth investigations of the key characteristics of trustworthy AI, including transparency, fairness, reliability, privacy, safety, robustness, and more A close look at the potential pitfalls, challenges, and stakeholder concerns that impact trust in AI application Best practices, mechanisms, and governance considerations for embedding AI ethics in business processes and decision making Written to inform executives, managers, and other business leaders, Trustworthy AI breaks new ground as an essential resource for all organizations using AI.
Author: Ben Shneiderman Publisher: Oxford University Press ISBN: 0192845292 Category : Computers Languages : en Pages : 390
Book Description
The remarkable progress in algorithms for machine and deep learning have opened the doors to new opportunities, and some dark possibilities. However, a bright future awaits those who build on their working methods by including HCAI strategies of design and testing. As many technology companies and thought leaders have argued, the goal is not to replace people, but to empower them by making design choices that give humans control over technology. In Human-Centered AI, Professor Ben Shneiderman offers an optimistic realist's guide to how artificial intelligence can be used to augment and enhance humans' lives. This project bridges the gap between ethical considerations and practical realities to offer a road map for successful, reliable systems. Digital cameras, communications services, and navigation apps are just the beginning. Shneiderman shows how future applications will support health and wellness, improve education, accelerate business, and connect people in reliable, safe, and trustworthy ways that respect human values, rights, justice, and dignity.
Author: Shubham Sharma (Ph. D.) Publisher: ISBN: Category : Languages : en Pages : 0
Book Description
As artificial intelligence (AI) systems increasingly impact the society, it is important to design and maintain models that are responsible and trustworthy. Models should not discriminate against certain individuals or a group of individuals (fairness), the decisions should be explainable, and they should be robust to adversarial attacks. Moreover, the trained models should be dynamically updated if the data changes over time, and methods to provide explanations for model decisions need to operate efficiently and in real-time. In this thesis, we address these challenges by developing frameworks that can account for more than one characteristic of responsible artificial intelligence. First, we evaluate existing black-box models using CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of AI models. CERTIFAI uses a custom genetic algorithm to produce counterfactual explanations, which are generated points close to the input point but belonging to a different class. These points can then be used to: provide explanations, measure feature importance, evaluate fairness based on an introduced notion called burden, and measure the robustness to adversarial attacks. We then introduce FASTER-CE: a novel set of algorithms to generate fast, sparse, and robust counterfactual explanations. The backbone of the proposed method is an autoencoder trained on the original dataset. Random samples from the latent space of the trained autoencoder are used to train linear models for each of the features in the dataset and for the black-box model predictions. Using these trained linear models and additional user-defined constraints, we easily compute the direction for counterfactual explanation search and generate multiple counterfactual explanations that are sparse, realistic, and robust to input manipulations. We show that FASTER-CE is much faster than other state of the art methods to generate counterfactual explanations in generating multiple explanations with several desirable, and often conflicting, properties. Additionally, we explore the trade-offs between the sparsity, proximity, validity, speed of generation, and the robustness of explanations. Next, we look into training a fairer model by creating a data augmentation based pre-processing bias mitigation technique that also lends itself towards bias disambiguation called FaiDA (fair data augmentation). We theoretically show that two different notions of fairness: statistical parity difference (independence) and average odds difference (separation) always change in the same direction using such an augmentation. We also show submodularity of the proposed fairness-aware augmentation approach that enables an efficient greedy algorithm. To make models fair and robust, we introduce an in-processing bias mitigation technique FaiR-N: Fair and Robust Neural Networks, that trains models with regularizers to improve on burden-based fairness and adversarial robustness. We show that models can be trained with these considerations without compromising significantly on accuracy, that improving on burden based fairness also improves other fairness measures, and also discuss trade-offs between fairness and adversarial robustness. We then focus on training models that are more fair and can also account for drift, where the drift could be with respect to accuracy and fairness. We propose FEAMOE, a mixture of experts framework aimed at learning fairer, more interpretable models that can also rapidly adjust to drifts in both the accuracy and fairness of a classifier. We illustrate our framework for three popular fairness measures and demonstrate how drift can be handled with respect to these fairness constraints, while also providing fast explanations. Our framework, as applied to a mixture of linear experts, is able to perform comparably to neural networks in terms of accuracy while producing fairer and more interpretable models that are dynamically updated to account for drift
Author: Arnaldo Pérez Castaño Publisher: Apress ISBN: 1484233573 Category : Computers Languages : en Pages : 701
Book Description
Discover how all levels Artificial Intelligence (AI) can be present in the most unimaginable scenarios of ordinary lives. This book explores subjects such as neural networks, agents, multi agent systems, supervised learning, and unsupervised learning. These and other topics will be addressed with real world examples, so you can learn fundamental concepts with AI solutions and apply them to your own projects. People tend to talk about AI as something mystical and unrelated to their ordinary life. Practical Artificial Intelligence provides simple explanations and hands on instructions. Rather than focusing on theory and overly scientific language, this book will enable practitioners of all levels to not only learn about AI but implement its practical uses. What You’ll Learn Understand agents and multi agents and how they are incorporated Relate machine learning to real-world problems and see what it means to you Apply supervised and unsupervised learning techniques and methods in the real world Implement reinforcement learning, game programming, simulation, and neural networks Who This Book Is For Computer science students, professionals, and hobbyists interested in AI and its applications.
Author: Yada Pruksachatkun
Author: Yada Pruksachatkun
Author: Yada Pruksachatkun
Author: Kush R. Vashney
Author: Bhavya Kailkhura
Author: Lam M. Nguyen
Author: Thai Quang Le
Author: Beena Ammanath
Author: Ben Shneiderman
Author: Shubham Sharma (Ph. D.)
Author: Arnaldo Pérez Castaño