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

 
Scikit-Learn、Keras和TensorFlow的機(jī)器學(xué)習(xí)實用指南（第3版，影印版）
Scikit-Learn、Keras和TensorFlow的機(jī)器學(xué)習(xí)實用指南（第3版，影印版）
Aurélien Géron 著
出版時間：2023年03月
頁數(shù)：834
“研究機(jī)器學(xué)習(xí)的絕佳資源。你會從中發(fā)現(xiàn)清晰直觀的解釋以及大量的實用技巧?！?br /> -Francois Chollet
深度學(xué)習(xí)庫Keras的作者，Deep Learning with Python
一書的作者
“這本書出色地介紹了神經(jīng)網(wǎng)絡(luò)的理論和實踐；推薦給任何對實用機(jī)器學(xué)習(xí)有興趣的讀者?！?br /> -Pete Warden
TensorFlow的移動端負(fù)責(zé)人

通過一系列最新的技術(shù)突破，深度學(xué)習(xí)推動了整個機(jī)器學(xué)習(xí)領(lǐng)域的發(fā)展?，F(xiàn)在，即使是對這項技術(shù)幾乎一無所知的程序員也可以使用簡單、高效的工具來實現(xiàn)具備數(shù)據(jù)學(xué)習(xí)能力的程序。這本暢銷書采用具體示例、最小化理論和生產(chǎn)就緒的Python框架（Scikit-Learn、Keras和TensorFlow）來幫助你直觀地理解構(gòu)建智能系統(tǒng)的概念和工具。
在更新的第3版中，作者Aurélien Géron探究了一系列技術(shù)，從簡單的線性回歸開始，逐步推進(jìn)到深度神經(jīng)網(wǎng)絡(luò)。書中的大量代碼示例和練習(xí)有助于你學(xué)以致用。你需要具備一定的編程經(jīng)驗。
● 使用Scikit-Learn從頭到尾跟蹤一個機(jī)器學(xué)習(xí)示例項目
● 探索包括支持向量機(jī)、決策樹、隨機(jī)森林和集成方法在內(nèi)的多種模型
● 利用降維、聚類和異常檢測等無監(jiān)督學(xué)習(xí)技術(shù)
● 深入研究包括卷積網(wǎng)絡(luò)、遞歸網(wǎng)絡(luò)、生成對抗網(wǎng)絡(luò)、自動編碼器、擴(kuò)散模型和Transformers在內(nèi)的多種神經(jīng)網(wǎng)絡(luò)架構(gòu)
● 使用TensorFlow和Keras為計算機(jī)視覺、自然語言處理、生成模型和深度強(qiáng)化學(xué)習(xí)構(gòu)建和訓(xùn)練神經(jīng)網(wǎng)絡(luò)
  1. Preface
  2. Part I. The Fundamentals of Machine Learning
  3. 1. The Machine Learning Landscape
  4. What Is Machine Learning?
  5. Why Use Machine Learning?
  6. Examples of Applications
  7. Types of Machine Learning Systems
  8. Main Challenges of Machine Learning
  9. Testing and Validating
  10. Exercises
  11. 2. End-to-End Machine Learning Project
  12. Working with Real Data
  13. Look at the Big Picture
  14. Get the Data
  15. Explore and Visualize the Data to Gain Insights
  16. Prepare the Data for Machine Learning Algorithms
  17. Select and Train a Model
  18. Fine-Tune Your Model
  19. Launch, Monitor, and Maintain Your System
  20. Try It Out!
  21. Exercises
  22. 3. Classification
  23. MNIST
  24. Training a Binary Classifier
  25. Performance Measures
  26. Multiclass Classification
  27. Error Analysis
  28. Multilabel Classification
  29. Multioutput Classification
  30. Exercises
  31. 4. Training Model
  32. Linear Regression
  33. Gradient Descent
  34. Polynomial Regression
  35. Learning Curves
  36. Regularized Linear Models
  37. Logistic Regression
  38. Exercises
  39. 5. Support Vector Machines
  40. Linear SVM Classification
  41. Nonlinear SVM Classification
  42. SVM Regression
  43. Under the Hood of Linear SVM Classifiers
  44. The Dual Problem
  45. Exercises
  46. 6. Decision Trees
  47. Training and Visualizing a Decision Tree
  48. Making Predictions
  49. Estimating Class Probabilities
  50. The CART Training Algorithm
  51. Computational Complexity
  52. Gini Impurity or Entropy?
  53. Regularization Hyperparameters
  54. Regression
  55. Sensitivity to Axis Orientation
  56. Decision Trees Have a High Variance
  57. Exercises
  58. 7. Ensemble Learning and Random Forests
  59. Voting Classifiers
  60. Bagging and Pasting
  61. Random Forests
  62. Boosting
  63. Stacking
  64. Exercises
  65. 8. Dimensionality Reduction
  66. The Curse of Dimensionality
  67. Main Approaches for Dimensionality Reduction
  68. PCA
  69. Random Projection
  70. LLE
  71. Other Dimensionality Reduction Techniques
  72. Exercises
  73. 9. Unsupervised Learning Techniques
  74. Clustering Algorithms: k-means and DBSCAN
  75. Gaussian Mixtures
  76. Exercises
  77. Part II. Neural Networks and Deep Learning
  78. 10. Introduction to Artificial Neural Networks with Keras
  79. From Biological to Artificial Neurons
  80. Implementing MLPs with Keras
  81. Fine-Tuning Neural Network Hyperparameters
  82. Exercises
  83. 11. Training Deep Neural Networks
  84. The Vanishing/Exploding Gradients Problems
  85. Reusing Pretrained Layers
  86. Faster Optimizers
  87. Learning Rate Scheduling
  88. Avoiding Overfitting Through Regularization
  89. Summary and Practical Guidelines
  90. Exercises
  91. 12. Custom Models and Training with TensorFlow
  92. A Quick Tour of TensorFlow
  93. Using TensorFlow like NumPy
  94. Customizing Models and Training Algorithms
  95. TensorFlow Functions and Graphs
  96. Exercises
  97. 13. Loading and Preprocessing Data with TensorFlow
  98. The tf.data API
  99. The TFRecord Format
  100. Keras Preprocessing Layers
  101. The TensorFlow Datasets Project
  102. Exercises
  103. 14. Deep Computer Vision Using Convolutional Neural Networks
  104. The Architecture of the Visual Cortex
  105. Convolutional Layers
  106. Pooling Layers
  107. Implementing Pooling Layers with Keras
  108. CNN Architectures
  109. Implementing a ResNet-34 CNN Using Keras
  110. Using Pretrained Models from Keras
  111. Pretrained Models for Transfer Learning
  112. Classification and Localization
  113. Object Detection
  114. Object Tracking
  115. Semantic Segmentation
  116. Exercises
  117. 15. Processing Sequences Using RNNs and CNNs
  118. Recurrent Neurons and Layers
  119. Training RNNs
  120. Forecasting a Time Series
  121. Handling Long Sequences
  122. Exercises
  123. 16. Natural Language Processing with RNNs and Attention
  124. Generating Shakespearean Text Using a Character RNN
  125. Sentiment Analysis
  126. An Encoder–Decoder Network for Neural Machine Translation
  127. Attention Mechanisms
  128. An Avalanche of Transformer Models
  129. Vision Transformers
  130. Hugging Face’s Transformers Library
  131. Exercises
  132. 17. Autoencoders, GANs, and Diffusion Models
  133. Efficient Data Representations
  134. Performing PCA with an Undercomplete Linear Autoencoder
  135. Stacked Autoencoders
  136. Convolutional Autoencoders
  137. Denoising Autoencoders
  138. Sparse Autoencoders
  139. Variational Autoencoders
  140. Generating Fashion MNIST Images
  141. Generative Adversarial Networks
  142. Diffusion Models
  143. Exercises
  144. 18. Reinforcement Learning
  145. Learning to Optimize Rewards
  146. Policy Search
  147. Introduction to OpenAI Gym
  148. Neural Network Policies
  149. Evaluating Actions: The Credit Assignment Problem
  150. Policy Gradients
  151. Markov Decision Processes
  152. Temporal Difference Learning
  153. Q-Learning
  154. Implementing Deep Q-Learning
  155. Deep Q-Learning Variants
  156. Overview of Some Popular RL Algorithms
  157. Exercises
  158. 19. Training and Deploying TensorFlow Models at Scale
  159. Serving a TensorFlow Model
  160. Deploying a Model to a Mobile or Embedded Device
  161. Running a Model in a Web Page
  162. Using GPUs to Speed Up Computations
  163. Training Models Across Multiple Devices
  164. Exercises
  165. Thank You!
  166. A. Machine Learning Project Checklist
  167. B. Autodiff
  168. C. Special Data Structures
  169. D. TensorFlow Graphs
  170. Index
書名：Scikit-Learn、Keras和TensorFlow的機(jī)器學(xué)習(xí)實用指南（第3版，影印版）
作者：Aurélien Géron 著
國內(nèi)出版社：東南大學(xué)出版社
出版時間：2023年03月
頁數(shù)：834
書號：978-7-5766-0594-5
原版書書名：Hands-On Machine Learning with Scikit-Learn, Keras, and Tens
原版書出版商：O'Reilly Media
Aurélien Géron
 
Aurélien Géron是機(jī)器學(xué)習(xí)方面的顧問。他曾是Google軟件工程師，在2013年到2016年主導(dǎo)了YouTube視頻分類工程。2002年和2012年，他還是Wifirst公司（一家法國的無線ISP）的創(chuàng)始人和首席技術(shù)官，2001年是Ployconseil公司（現(xiàn)在管理電動汽車共享服務(wù)Autolib）的創(chuàng)始人和首席技術(shù)官。
 
 
The animal on the cover of Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow is the fire salamander (Salamandra salamandra), an amphibian found across most of Europe. Its black, glossy skin features large yellow spots on the head and back, signaling the presence of alkaloid toxins. This is a possible source of this amphibian’s common name: contact with these toxins (which they can also spray short distances) causes convulsions and hyperventilation. Either the painful poisons or the moistness of the salamander’s skin (or both) led to a misguided belief that these creatures not only could survive being placed in fire but could extinguish it as well.
Fire salamanders live in shaded forests, hiding in moist crevices and under logs near the pools or other freshwater bodies that facilitate their breeding. Though they spend most of their lives on land, they give birth to their young in water. They subsist mostly on a diet of insects, spiders, slugs, and worms. Fire salamanders can grow up to a foot in length, and in captivity may live as long as 50 years.
The fire salamander’s numbers have been reduced by destruction of their forest habitat and capture for the pet trade, but the greatest threat they face is the susceptibility of their moisture-permeable skin to pollutants and microbes. Since 2014, they have become extinct in parts of the Netherlands and Belgium due to an introduced fungus.
購買選項
定價：199.00元
書號：978-7-5766-0594-5
出版社：東南大學(xué)出版社