Practicing Trustworthy Machine Learning: Consistent, Transparent, and Fair AI Pipelines
暫譯: 實踐可信賴的機器學習：一致性、透明性與公平的 AI 流程
Pruksachatkun, Yada, McAteer, Matthew, Majumdar, Subhabrata
- 出版商: O'Reilly
- 出版日期: 2023-02-07
- 定價: $2,690
- 售價: 8.8 折 $2,367 (限時優惠至 2025-03-31)
- 語言: 英文
- 頁數: 350
- 裝訂: Quality Paper - also called trade paper
- ISBN: 1098120272
- ISBN-13: 9781098120276
-
相關分類:
人工智慧、Machine Learning
立即出貨 (庫存 < 3)
商品描述
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
商品描述(中文翻譯)
隨著人工智慧在醫療、法律和國防等高風險領域的使用日益增加，組織花費大量時間和金錢來使機器學習（ML）模型值得信賴。許多相關書籍深入探討理論和概念。本指南提供了一個實用的起點，幫助開發團隊製作安全性更高、穩健性更強、偏見更少且更具可解釋性的模型。
作者 Yada Pruksachatkun、Matthew McAteer 和 Subhabrata Majumdar 將學術文獻中關於策劃數據集和構建模型的最佳實踐轉化為建立行業級可信機器學習系統的藍圖。通過這本書，工程師和數據科學家將獲得在嘈雜、混亂且經常充滿敵意的世界中釋放可信機器學習應用所需的基礎。
您將學到：
- 向利益相關者解釋機器學習模型及其輸出的方法
- 如何識別和修正機器學習流程中的公平性問題和隱私洩漏
- 如何開發對惡意攻擊穩健且安全的機器學習系統
- 重要的系統性考量，例如如何管理信任債務以及哪些機器學習障礙需要人類介入
作者簡介
Yada Pruksachatkun is a machine learning scientist at Infinitus, a conversational AI startup that automates calls in the healthcare system. She has worked on trustworthy natural language processing as an Applied Scientist at Amazon, and led the first healthcare NLP initiative within mid-sized startup ASAPP. She did research transfer learning in NLP in graduate school at NYU and was advised by Professor Sam Bowman.
Matthew McAteer is the creator of 5cube Labs, an ML consultancy that has worked with over 100 companies in industries ranging from architecture to medicine to agriculture. Matthew worked with the Tensorflow team at Google on probabilistic programming, and previously worked in biomedical research in labs at MIT and Harvard Medical School.
Subhabrata (Subho) Majumdar is a Senior Applied Scientist at Splunk. Previously, he spent 3 years in AT&T, where he led research and development on ethical AI. Subho deeply believes in the power of data to bring about positive changes in the world---he has cofounded the Trustworthy ML Initiative, and has been a part of multiple successful industry-academia collaborations in the data for good space. Subho holds a PhD in Statistics from the University of Minnesota.
作者簡介(中文翻譯)
Yada Pruksachatkun 是 Infinitus 的機器學習科學家，這是一家自動化醫療系統通話的對話式人工智慧初創公司。她曾在亞馬遜擔任應用科學家，專注於可信的自然語言處理，並在中型初創公司 ASAPP 領導了首個醫療保健 NLP 項目。她在紐約大學的研究生院進行了自然語言處理中的遷移學習研究，並受到 Sam Bowman 教授的指導。
Matthew McAteer 是 5cube Labs 的創始人，這是一家機器學習顧問公司，曾與超過 100 家來自建築、醫療和農業等行業的公司合作。Matthew 曾與谷歌的 Tensorflow 團隊合作進行概率編程，並在麻省理工學院和哈佛醫學院的實驗室從事生物醫學研究。
Subhabrata (Subho) Majumdar 是 Splunk 的高級應用科學家。此前，他在 AT&T 工作了 3 年，負責倫理人工智慧的研究與開發。Subho 深信數據能帶來世界的積極變化——他共同創立了可信機器學習倡議，並參與了多個成功的產業與學術合作，致力於數據為善的領域。Subho 擁有明尼蘇達大學的統計學博士學位。
