面向工程师的实用机器学习和AI（影印版）
面向工程师的实用机器学习和AI（影印版）
Jeff Prosise 著
出版时间：2023年03月
页数：400
“如果你想搞明白AI和机器学习究竟是如何工作的，以及这些技术的演变历程和未来发展，那就读读这本书吧。”
——Todd Fine
Atmosera首席战略官“读了这本书会让你忍不住跃跃欲试。”
——Doug Turnure
Microsoft Azure专家

许多AI入门指南可以说都是变相的微积分书籍，但这本书基本上避开了数学。作者Jeff......展开全部内容介绍
  1. Foreword
  2. Preface
  3. Part I. Machine Learning with Scikit-Learn
  4. 1. Machine Learning
  5. What Is Machine Learning?
  6. Unsupervised Learning with k-Means Clustering
  7. Supervised Learning
  8. Summary
  9. 2. Regression Models
  10. Linear Regression
  11. Decision Trees
  12. Random Forests
  13. Gradient-Boosting Machines
  14. Support Vector Machines
  15. Accuracy Measures for Regression Models
  16. Using Regression to Predict Taxi Fares
  17. Summary
  18. 3. Classification Models
  19. Logistic Regression
  20. Accuracy Measures for Classification Models
  21. Categorical Data
  22. Binary Classification
  23. Multiclass Classification
  24. Building a Digit Recognition Model
  25. Summary
  26. 4. Text Classification
  27. Preparing Text for Classification
  28. Sentiment Analysis
  29. Naive Bayes
  30. Spam Filtering
  31. Recommender Systems
  32. Summary
  33. 5. Support Vector Machines
  34. How Support Vector Machines Work
  35. Hyperparameter Tuning
  36. Data Normalization
  37. Pipelining
  38. Using SVMs for Facial Recognition
  39. Summary
  40. 6. Principal Component Analysis
  41. Understanding Principal Component Analysis
  42. Filtering Noise
  43. Anonymizing Data
  44. Visualizing High-Dimensional Data
  45. Anomaly Detection
  46. Summary
  47. 7. Operationalizing Machine Learning Models
  48. Consuming a Python Model from a Python Client
  49. Versioning Pickle Files
  50. Consuming a Python Model from a C# Client
  51. Containerizing a Machine Learning Model
  52. Using ONNX to Bridge the Language Gap
  53. Building ML Models in C# with ML.NET
  54. Adding Machine Learning Capabilities to Excel
  55. Summary
  56. Part II. Deep Learning with Keras and TensorFlow
  57. 8. Deep Learning
  58. Understanding Neural Networks
  59. Training Neural Networks
  60. Summary
  61. 9. Neural Networks
  62. Building Neural Networks with Keras and TensorFlow
  63. Binary Classification with Neural Networks
  64. Multiclass Classification with Neural Networks
  65. Training a Neural Network to Recognize Faces
  66. Dropout
  67. Saving and Loading Models
  68. Keras Callbacks
  69. Summary
  70. 10. Image Classification with Convolutional Neural Networks
  71. Understanding CNNs
  72. Pretrained CNNs
  73. Using ResNet50V2 to Classify Images
  74. Transfer Learning
  75. Using Transfer Learning to Identify Arctic Wildlife
  76. Data Augmentation
  77. Global Pooling
  78. Audio Classification with CNNs
  79. Summary
  80. 11. Face Detection and Recognition
  81. Face Detection
  82. Facial Recognition
  83. Putting It All Together: Detecting and Recognizing Faces in Photos
  84. Handling Unknown Faces: Closed-Set Versus Open-Set Classification
  85. Summary
  86. 12. Object Detection
  87. R-CNNs
  88. Mask R-CNN
  89. YOLO
  90. YOLOv3 and Keras
  91. Custom Object Detection
  92. Summary
  93. 13. Natural Language Processing
  94. Text Preparation
  95. Word Embeddings
  96. Text Classification
  97. Neural Machine Translation
  98. Bidirectional Encoder Representations from Transformers (BERT)
  99. Summary
  100. 14. Azure Cognitive Services
  101. Introducing Azure Cognitive Services
  102. The Computer Vision Service
  103. The Language Service
  104. The Translator Service
  105. The Speech Service
  106. Putting It All Together: Contoso Travel
  107. Summary
  108. Index
购买选项
定价：158.00元
书号：978-7-5766-0657-7
出版社：东南大学出版社
联系出版社邮购

© 2025，奥莱利技术咨询(北京)有限公司。版权所有。
传真: +86-10-88097463
 京ICP备05003502号