Python Machine Learning, 2/e (Paperback)

Sebastian Raschka, Vahid Mirjalili

買這商品的人也買了...

商品描述

Key Features

  • Second edition of the bestselling book on Machine Learning
  • A practical approach to the frameworks of data science, machine learning, and deep learning
  • Use the most powerful Python libraries to implement machine learning and deep learning
  • Learn best practices to improve and optimize your machine learning systems and algorithms

Book Description

Machine learning is eating the software world, and now deep learning is extending machine learning. This book is for developers and data scientists who want to master the world of artificial intelligence, with a practical approach to understanding and implementing machine learning, and how to apply the power of deep learning with Python.

This Second Edition of Sebastian Raschka's Python Machine Learning is thoroughly updated to use the most powerful and modern Python open-source libraries, so that you can understand and work at the cutting-edge of machine learning, neural networks, and deep learning.

Written for developers and data scientists who want to create practical machine learning code, the authors have extended and modernized this best-selling book, to now include the influential TensorFlow library, and the Keras Python neural network library. The Scikit-learn code has also been fully updated to include recent innovations. The result is a new edition of this classic book at the cutting edge of machine learning.

Readers new to machine learning will find this classic book offers the practical knowledge and rich techniques they need to create and contribute to machine learning, deep learning, and modern data analysis. Raschka and Mirjalili introduce you to machine learning and deep learning algorithms, and show you how to apply them to practical industry challenges. By the end of the book, you'll be ready to meet the new data analysis opportunities in today's world .

Readers of the first edition will be delighted to find a new balance of classical ideas and modern insights into machine learning. Every chapter has been critically updated, and there are new chapters on key technologies. Readers can learn and work with TensorFlow more deeply than ever before, and essential coverage of the Keras neural network library has been added, along with the most recent updates to Scikit-learn. Raschka and Mirjalili have updated this book to meet the most modern areas of machine learning, to give developers and data scientists a fresh and practical Python journey into machine learning.

What you will learn

  • Use the key frameworks of data science, machine learning, and deep learning
  • Ask new questions of your data through machine learning models and neural networks
  • Work with the most powerful Python open-source libraries in machine learning
  • Build deep learning applications using Keras and TensorFlow
  • Embed your machine learning model in accessible web applications
  • Predict continuous target outcomes using regression analysis
  • Uncover hidden patterns and structures in data with clustering
  • Analyze images using deep learning techniques
  • Use sentiment analysis to delve deeper into textual and social media data

商品描述(中文翻譯)

主要特點


  • 暢銷機器學習書籍的第二版

  • 實用的數據科學、機器學習和深度學習框架方法

  • 使用最強大的Python庫實現機器學習和深度學習

  • 學習改進和優化機器學習系統和算法的最佳實踐

書籍描述

機器學習正在改變軟體世界,現在深度學習正在擴展機器學習。本書針對開發人員和數據科學家,以實用的方法來理解和實現機器學習,以及如何應用Python的深度學習能力。

Sebastian Raschka的《Python機器學習》第二版已經全面更新,使用最強大和現代的Python開源庫,讓您能夠理解並在機器學習、神經網絡和深度學習的前沿工作。

本書針對希望創建實用機器學習代碼的開發人員和數據科學家進行了擴展和現代化,現在包括了具有影響力的TensorFlow庫和Keras Python神經網絡庫。Scikit-learn代碼也已完全更新,包括最新的創新。結果是這本經典書籍的新版處於機器學習的前沿。

對於初學機器學習的讀者來說,這本經典書籍提供了他們創建和貢獻於機器學習、深度學習和現代數據分析所需的實用知識和豐富技巧。Raschka和Mirjalili向您介紹機器學習和深度學習算法,並向您展示如何應用它們解決實際的行業挑戰。通過閱讀本書,您將準備好應對當今世界中的新數據分析機會。

第一版讀者將高興地發現,這本書在傳統思想和現代機器學習見解之間取得了新的平衡。每一章都經過了重要的更新,並增加了關鍵技術的新章節。讀者可以比以往更深入地學習和使用TensorFlow,並添加了對Keras神經網絡庫的重要覆蓋,以及Scikit-learn的最新更新。Raschka和Mirjalili已經更新了這本書,以滿足機器學習的最新領域,為開發人員和數據科學家提供了一次新鮮而實用的Python之旅。

你將學到什麼


  • 使用數據科學、機器學習和深度學習的關鍵框架

  • 通過機器學習模型和神經網絡對數據提出新的問題

  • 使用機器學習中最強大的Python開源庫

  • 使用Keras和TensorFlow構建深度學習應用

  • 將機器學習模型嵌入易於訪問的Web應用程序

  • 使用回歸分析預測連續目標結果

  • 使用聚類發現數據中的隱藏模式和結構

  • 使用深度學習技術分析圖像

  • 使用情感分析深入研究文本和社交媒體數據