91精品国产综合久久四虎久久_国产成人午夜高潮毛片_99er视频精品免费观看_2020亚洲熟女在线观看_日本女优人体写真_国内黄色毛片_年轻的老师中文版在线_丰满女邻居做爰_久久久久久精品成人免费图片

 
面向工程師的實用機器學習和AI（影印版）
面向工程師的實用機器學習和AI（影印版）
Jeff Prosise 著
出版時間：2023年03月
頁數(shù)：400
“如果你想搞明白AI和機器學習究竟是如何工作的，以及這些技術的演變歷程和未來發(fā)展，那就讀讀這本書吧?！?br /> ——Todd Fine
Atmosera首席戰(zhàn)略官“讀了這本書會讓你忍不住躍躍欲試?！?br /> ——Doug Turnure
Microsoft Azure專家

許多AI入門指南可以說都是變相的微積分書籍，但這本書基本上避開了數(shù)學。作者Jeff Prosise幫助工程師和軟件開發(fā)人員建立了對AI的直觀理解，以解決商業(yè)問題。需要創(chuàng)建一個系統(tǒng)來檢測雨林中非法砍伐的聲音、分析文本的情感或預測旋轉機械的早期故障？這本實踐用書將教你把AI和機器學習應用于職場工作所需的技能。
書中的示例和插圖來自于Prosise在全球多家公司和研究機構教授的AI和機器學習課程。不說廢話，也沒有可怕的公式 —— 純粹就是寫給工程師和軟件開發(fā)人員的快速入門，并附有實際操作的例子。
本書將幫助你：
● 學習什么是機器學習和深度學習及其用途
● 理解流行的機器學習算法原理及其應用場景
● 使用Scikit-Learn在Python中構建機器學習模型，使用Keras和TensorFlow構建神經網(wǎng)絡
● 訓練回歸模型以及二元和多元分類模型并給其評分
● 構建面部識別模型和目標檢測模型
● 構建能夠響應自然語言查詢并將文本翻譯成其他語言的語言模型
● 使用認知服務將AI融入你編寫的應用程序中
  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
書名：面向工程師的實用機器學習和AI（影印版）
作者：Jeff Prosise 著
國內出版社：東南大學出版社
出版時間：2023年03月
頁數(shù)：400
書號：978-7-5766-0657-7
原版書書名：Applied Machine Learning and AI for Engineers
原版書出版商：O'Reilly Media
Jeff Prosise
 
Jeff Prosise是個多面手。作為工程師，他熱衷于向其他工程師和軟件開發(fā)人員宣傳人工智能和機器學習的奇跡。他是Wintellect 公司的聯(lián)合創(chuàng)始人，寫過9本書，在雜志上發(fā)表過好幾百篇文章，在微軟培訓過幾千名開發(fā)人員，并在一些規(guī)模比較大的全球軟件大會上發(fā)表過演講。
另一方面，杰夫在美國橡樹嶺國家實驗室和勞倫斯利弗莫爾國家實驗室從事高功率激光系統(tǒng)和聚變能源研究。業(yè)余時間，他很喜歡大型遙控噴氣式飛機的組裝和試飛，還經常前往全球潛水勝地去打卡。2021年公司被收購后，杰夫出任Atmosera公司首席學習官，幫助客戶將AI集成到產品中。
 
 
The animal on the cover of Applied Machine Learning and AI for Engineers is a festive parrot (Amazona festiva), also known as a festive amazon. Festive parrots live in the tropical forests, woodlands, and coastal mangroves of several South American countries, including Brazil, Colombia, Ecuador, Peru, and Bolivia. They are rarely found far from water.
Festive parrots are brightly—you might even say festively—colored, medium-sized birds. Their plumage is predominantly a striking green, turning slightly yellow toward the edges of their wings. A motley assortment of colors—including red, blue, and sometimes yellow or orange—adorns their faces.
Festive parrots are a highly social species, usually spotted in pairs or small flocks. Large groups of the birds often gather at night for communal roosts or around a localized food source and are known for being incredibly noisy. They enjoy eating fruits such as mangoes and peach palm, with berries, nuts, seeds, flowers, and leaf buds supplementing their diet.
While still relatively common where their forest habitat remains largely intact, festive parrots have been categorized by IUCN as near threatened due to continued deforestation and predicted declines in habitat.
購買選項
定價：158.00元
書號：978-7-5766-0657-7
出版社：東南大學出版社