Explainable AI Recipes: Implement Solutions to Model Explainability and Interpretability with Python
Mishra, Pradeepta
相關主題
商品描述
Understand how to use Explainable AI (XAI) libraries and build trust in AI and machine learning models. This book utilizes a problem-solution approach to explaining machine learning models and their algorithms.
The book starts with model interpretation for supervised learning linear models, which includes feature importance, partial dependency analysis, and influential data point analysis for both classification and regression models. Next, it explains supervised learning using non-linear models and state-of-the-art frameworks such as SHAP values/scores and LIME for local interpretation. Explainability for time series models is covered using LIME and SHAP, as are natural language processing-related tasks such as text classification, and sentiment analysis with ELI5, and ALIBI. The book concludes with complex model classification and regression-like neural networks and deep learning models using the CAPTUM framework that shows feature attribution, neuron attribution, and activation attribution.
After reading this book, you will understand AI and machine learning models and be able to put that knowledge into practice to bring more accuracy and transparency to your analyses.
What You Will Learn
- Create code snippets and explain machine learning models using Python
- Leverage deep learning models using the latest code with agile implementations
- Build, train, and explain neural network models designed to scale
- Understand the different variants of neural network models
Who This Book Is For
AI engineers, data scientists, and software developers interested in XAI
商品描述(中文翻譯)
了解如何使用可解釋的人工智慧（XAI）程式庫並建立對人工智慧和機器學習模型的信任。本書採用問題解決的方式來解釋機器學習模型及其演算法。
本書首先介紹了監督式學習線性模型的模型解釋，包括特徵重要性、部分相依性分析以及對於分類和回歸模型的影響數據點分析。接下來，本書解釋了使用非線性模型的監督式學習，以及使用最先進的框架（如SHAP值/分數和LIME）進行局部解釋。本書還介紹了使用LIME和SHAP進行時間序列模型的解釋，以及與自然語言處理相關的任務，如文本分類和情感分析，使用ELI5和ALIBI。最後，本書介紹了使用CAPTUM框架的複雜模型分類和類似神經網絡和深度學習模型，該框架展示了特徵歸因、神經元歸因和激活歸因。
閱讀本書後，您將了解人工智慧和機器學習模型，並能夠將這些知識應用於實踐，以提高分析的準確性和透明度。
- 使用Python創建程式碼片段並解釋機器學習模型
- 利用最新的代碼和敏捷實現來利用深度學習模型
- 構建、訓練和解釋設計用於擴展的神經網絡模型
- 了解不同變體的神經網絡模型
對XAI感興趣的人工智慧工程師、數據科學家和軟件開發人員。
作者簡介
Pradeepta Mishra is the Director of AI, Fosfor at L&T Infotech (LTI). He leads a large group of data scientists, computational linguistics experts, and machine learning and deep learning experts in building the next-generation product--Leni--which is the world's first virtual data scientist. He has expertise across core branches of artificial intelligence, including autonomous ML and deep learning pipelines, ML ops, image processing, audio processing, natural language processing (NLP), natural language generation (NLG), design and implementation of expert systems, and personal digital assistants (PDAs). In 2019 and 2020, he was named one of "India's Top 40 Under 40 Data Scientists" by Analytics India magazine. Two of his books have been translated into Chinese and Spanish, based on popular demand.
Pradeepa delivered a keynote session at the Global Data Science Conference 2018, USA. He delivered a TEDx talk on "Can Machines Think?", available on the official TEDx YouTube channel. He has mentored more than 2,000 data scientists globally. He has delivered 200+ tech talks on data science, ML, DL, NLP, and AI at various universities, meetups, technical institutions, and community-arranged forums. He is a visiting faculty member to more than 10 universities, where he teaches deep learning and machine learning to professionals, and mentors them in pursuing a rewarding career in artificial intelligence.
作者簡介(中文翻譯)
Pradeepta Mishra是L&T Infotech（LTI）的AI Fosfor部門主管。他帶領一個由數據科學家、計算語言學專家以及機器學習和深度學習專家組成的大型團隊，致力於打造下一代產品Leni，這是世界上第一個虛擬數據科學家。他在人工智能的核心領域具有專業知識，包括自主機器學習和深度學習流程、機器學習運營、圖像處理、音頻處理、自然語言處理（NLP）、自然語言生成（NLG）、專家系統的設計和實施，以及個人數字助手（PDAs）。2019年和2020年，他被《Analytics India》雜誌評為「印度40位40歲以下的頂尖數據科學家」之一。根據廣大需求，他的兩本書已經被翻譯成中文和西班牙文。
Pradeepta在2018年的全球數據科學大會（Global Data Science Conference）上發表了主題演講。他在官方TEDx YouTube頻道上發表了一場名為「機器能思考嗎？」的TEDx演講。他在全球指導了2000多名數據科學家。他在各個大學、聚會、技術機構和社區組織的論壇上發表了200多場關於數據科學、機器學習、深度學習、自然語言處理和人工智能的技術演講。他是10多所大學的客座教師，教授專業人士深度學習和機器學習，並指導他們在人工智能領域追求有意義的職業生涯。
