欢迎光临澳大利亚新华书店网 [登录 | 免费注册]

    • 面向工程师的实用机器学习和AI(影印版)(英文版)
      • 作者:(美)杰夫·普洛西|责编:张烨
      • 出版社:东南大学
      • ISBN:9787576606577
      • 出版日期:2023/03/01
      • 页数:400
    • 售价:63.2
  • 内容大纲

        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 Prosise帮助工程师和软件开发人员建立了对AI的直观理解,以解决商业问题。需要创建一个系统来检测雨林中非法砍伐的声音、分析文本的情感或预测旋转机械的早期故障?这本实践用书将教你把AI和机器学习应用于职场工作所需的技能。
        书中的示例和插图来自于Prosise在全球多家公司和研究机构教授的AI和机器学习课程。不说废话,也没有可怕的公式——纯粹就是写给工程师和软件开发人员的快速入门,并附有实际操作的例子。
        本书将帮助你:
        ·学习什么是机器学习和深度学习及其用途
        ·理解流行的机器学习算法原理及其应用场景
        ·使用Scikit-Learn在Python中构建机器学习模型,使用Keras和TensorFlow构建神经网络
        ·训练回归模型以及二元和多元分类模型并给其评分
        ·构建面部识别模型和目标检测模型
        ·构建能够响应自然语言查询并将文本翻译成其他语言的语言模型
        ·使用认知服务将AI融入你编写的应用程序中
  • 作者介绍

        杰夫·普洛西(Jeff Prosise)是一名工程师,热衷于向工程师和软件开发人员介绍AI 和机器学习的种种神奇之处。作为Wintellect的联合创始人,他已经在微软培训了数千名开发人员,并在一些全球最大规模的软件会议上发表过演讲。此外,Jeff在橡树岭国家实验室和劳伦斯利弗莫尔国家实验室从事高功率激光系统和聚变能源研究。他目前担任Atmosera的首席学习官,帮助客户将AI融入他们的产品。
  • 目录

    Foreword
    Preface
    Part I.  Machine Learning with Scikit-Learn
      1. Machine Learning
        What Is Machine Learning?
          Machine Learning Versus Artificial Intelligence
          Supervised Versus Unsupervised Learning
        Unsupervised Learning with k-Means Clustering
          Applying k-Means Clustering to Customer Data
          Segmenting Customers Using More Than Two Dimensions
        Supervised Learning
          k-Nearest Neighbors
          Using k-Nearest Neighbors to Classify Flowers
        Summary
      2. Regression Models
        Linear Regression
        Decision Trees
        Random Forests
        Gradient-Boosting Machines
        Support Vector Machines
        Accuracy Measures for Regression Models
        Using Regression to Predict Taxi Fares
        Summary
      3. Classification Models
        Logistic Regression
        Accuracy Measures for Classification Models
        Categorical Data
        Binary Classification
          Classifying Passengers Who Sailed on the Titanic
          Detecting Credit Card Fraud
        Multiclass Classification
        Building a Digit Recognition Model
        Summary
      4. Text Classification
        Preparing Text for Classification
        Sentiment Analysis
        Naive Bayes
        Spam Filtering
        Recommender Systems
          Cosine Similarity
          Building a Movie Recommendation System
        Summary
      5. Support Vector Machines
        How Support Vector Machines Work
          Kernels
          Kernel Tricks
        Hyperparameter Tuning
        Data Normalization
        Pipelining
        Using SVMs for Facial Recognition

        Summary
      6. Principal Component Analysis
        Understanding Principal Component Analysis
        Filtering Noise
        Anonymizing Data
        Visualizing High-Dimensional Data
        Anomaly Detection
          Using PCA to Detect Credit Card Fraud
          Using PCA to Predict Bearing Failure
          Multivariate Anomaly Detection
        Summary
      7. Operationalizing Machine Learning Models
        Consuming a Python Model from a Python Client
        Versioning Pickle Files
        Consuming a Python Model from a C# Client
        Containerizing a Machine Learning Model
        Using ONNX to Bridge the Language Gap
        Building ML Models in C# with ML.NET
          Sentiment Analysis with ML.NET
          Saving and Loading ML.NET Models
        Adding Machine Learning Capabilities to Excel
        Summary
    Part II.  Deep Learning with Keras and TensorFlow
      8. Deep Learning
        Understanding Neural Networks
        Training Neural Networks
        Summary
      9. Neural Networks
        Building Neural Networks with Keras and TensorFlow
          Sizing a Neural Network
          Using a Neural Network to Predict Taxi Fares
        Binary Classification with Neural Networks
          Making Predictions
          Training a Neural Network to Detect Credit Card Fraud
        Multiclass Classification with Neural Networks
        Training a Neural Network to Recognize Faces
        Dropout
        Saving and Loading Models
        Keras Callbacks
        Summary
      10. Image Classification with Convolutional Neural Networks
        Understanding CNNs
          Using Keras and TensorFlow to Build CNNs
          Training a CNN to Recognize Arctic Wildlife
        Pretrained CNNs
        Using ResNet50V2 to Classify Images
        Transfer Learning
        Using Transfer Learning to Identify Arctic Wildlife
        Data Augmentation
          Image Augmentation with ImageDataGenerator

          Image Augmentation with Augmentation Layers
          Applying Image Augmentation to Arctic Wildlife
        Global Pooling
        Audio Classification with CNNs
        Summary
      11. Face Detection and Recognition
        Face Detection
          Face Detection with Viola-Jones
          Using the OpenCV Implementation of Viola-Jones
          Face Detection with Convolutional Neural Networks
          Extracting Faces from Photos
        Facial Recognition
          Applying Transfer Learning to Facial Recognition
          Boosting Transfer Learning with Task-Specific Weights
          ArcFace
        Putting It All Together: Detecting and Recognizing Faces in Photos
        Handling Unknown Faces: Closed-Set Versus Open-Set Classification
        Summary
      12. Object Detection
        R-CNNs
        Mask R-CNN
        YOLO
        YOLOv3 and Keras
        Custom Object Detection
          Training a Custom Object Detection Model with the Custom Vision Service
          Using the Exported Model
        Summary
      13. Natural Language Processing
        Text Preparation
        Word Embeddings
        Text Classification
          Automating Text Vectorization
          Using TextVectorization in a Sentiment Analysis Model
          Factoring Word Order into Predictions
          Recurrent Neural Networks (RNNs)
          Using Pretrained Models to Classify Text
        Neural Machine Translation
          LSTM Encoder-Decoders
          Transformer Encoder-Decoders
          Building a Transformer-Based NMT Model
          Using Pretrained Models to Translate Text
        Bidirectional Encoder Representations from Transformers (BERT)
          Building a BERT-Based Question Answering System
          Fine-Tuning BERT to Perform Sentiment Analysis
        Summary
      14. Azure Cognitive Services
        Introducing Azure Cognitive Services
          Keys and Endpoints
          Calling Azure Cognitive Services APls
          Azure Cognitive Services Containers

        The Computer Vision Service
        The Language Service
        The Translator Service
        The Speech Service
        Putting It All Together: Contoso Travel
        Summary
    Index