Machine Learning Refined: Foundations, Algorithms, and Applications, 2/e (Hardcover)

Watt, Jeremy, Borhani, Reza, Katsaggelos, Aggelos

  • 出版商: Cambridge
  • 出版日期: 2020-01-09
  • 售價: $1,680
  • 貴賓價: 9.8$1,646
  • 語言: 英文
  • 頁數: 594
  • 裝訂: Hardcover - also called cloth, retail trade, or trade
  • ISBN: 1108480721
  • ISBN-13: 9781108480727
  • 相關分類: Machine LearningAlgorithms-data-structures
  • 立即出貨 (庫存=1)



With its intuitive yet rigorous approach to machine learning, this text provides students with the fundamental knowledge and practical tools needed to conduct research and build data-driven products. The authors prioritize geometric intuition and algorithmic thinking, and include detail on all the essential mathematical prerequisites, to offer a fresh and accessible way to learn. Practical applications are emphasized, with examples from disciplines including computer vision, natural language processing, economics, neuroscience, recommender systems, physics, and biology. Over 300 color illustrations are included and have been meticulously designed to enable an intuitive grasp of technical concepts, and over 100 in-depth coding exercises (in Python) provide a real understanding of crucial machine learning algorithms. A suite of online resources including sample code, data sets, interactive lecture slides, and a solutions manual are provided online, making this an ideal text both for graduate courses on machine learning and for individual reference and self-study.

  • Encourages geometric intuition and algorithmic thinking to provide an intuitive understanding of key concepts and an interactive way of learning
  • Features coding exercises for Python to help put knowledge into practice
  • Emphasizes practical applications, with real-world examples, to give students the confidence to conduct research, build products, and solve problems
  • Completely self-contained, with appendices covering the essential mathematical prerequisites



- 鼓勵幾何直覺和算法思維,提供對關鍵概念的直觀理解和互動學習方式
- 提供Python編程練習,幫助將知識應用於實踐
- 強調實際應用,通過真實世界的例子,讓學生有信心進行研究、建立產品和解決問題
- 完全自包含,附錄涵蓋了必要的數學先備知識


Jeremy WattNorthwestern University, Illinois
Jeremy Watt received his Ph.D. in Electrical Engineering from Northwestern University, Illinois, and is now a machine learning consultant and educator. He teaches machine learning, deep learning, mathematical optimization, and reinforcement learning at Northwestern University, Illinois.

Reza BorhaniNorthwestern University, Illinois
Reza Borhani received his Ph.D. in Electrical Engineering from Northwestern University, Illinois, and is now a machine learning consultant and educator. He teaches a variety of courses in machine learning and deep learning at Northwestern University, Illinois.

Aggelos KatsaggelosNorthwestern University, Illinois
Aggelos K. Katsaggelos is the Joseph Cummings Professor at Northwestern University, Illinois, where he heads the Image and Video Processing Laboratory. He is a Fellow of Institute of Electrical and Electronics Engineers (IEEE), SPIE, the European Association for Signal Processing (EURASIP), and The Optical Society (OSA) and the recipient of the IEEE Third Millennium Medal (2000).


Jeremy Watt,來自伊利諾伊州西北大學,獲得電機工程博士學位,現為機器學習顧問和教育工作者。他在伊利諾伊州西北大學教授機器學習、深度學習、數學優化和強化學習等課程。

Reza Borhani,來自伊利諾伊州西北大學,獲得電機工程博士學位,現為機器學習顧問和教育工作者。他在伊利諾伊州西北大學教授多種機器學習和深度學習課程。

Aggelos K. Katsaggelos,是伊利諾伊州西北大學的Joseph Cummings教授,並領導圖像和視頻處理實驗室。他是電機和電子工程師學會(IEEE)、SPIE、歐洲信號處理協會(EURASIP)和光學學會(OSA)的會士,並獲得了IEEE第三千年獎章(2000年)。


1. Introduction to machine learning
Part I. Mathematical Optimization:
2. Zero order optimization techniques
3. First order methods
4. Second order optimization techniques
Part II. Linear Learning:
5. Linear regression
6. Linear two-class classification
7. Linear multi-class classification
8. Linear unsupervised learning
9. Feature engineering and selection
Part III. Nonlinear Learning:
10. Principles of nonlinear feature engineering
11. Principles of feature learning
12. Kernel methods
13. Fully-connected neural networks
14. Tree-based learners
Part IV. Appendices: Appendix A. Advanced first and second order optimization methods
Appendix B. Derivatives and automatic differentiation


1. 機器學習介紹
第一部分. 數學優化:
2. 零階優化技術
3. 一階方法
4. 二階優化技術
第二部分. 線性學習:
5. 線性回歸
6. 線性二元分類
7. 線性多元分類
8. 線性非監督學習
9. 特徵工程和選擇
第三部分. 非線性學習:
10. 非線性特徵工程原則
11. 特徵學習原則
12. 核方法
13. 全連接神經網絡
14. 基於樹的學習器
第四部分. 附錄: 附錄A. 高級一階和二階優化方法
附錄B. 導數和自動微分