Hands-on Machine Learning with Scikit-Learn,Keras TensorFlow

读书记录(缓慢更新)

目录

Part 1. The Fundamentals of Machine Learning

The Content of The Machine Learning Landscape

The Machine Learning Landscape

---

Part 1. The Fundamentals of Machine Learning

The Content of The Machine Learning Landscape

Part 1. The Fundamentals(fundament n.基础;臀部) of Machine Learning 机器学习的基础
1.The Machine Learning Landscape(n.景色;形势 v.对……做景观美化) 机器学习的前景
What Is Machine Learning? 什么是机器学习
Why Use Machine Learning? 为什么使用机器学习
Types of Machine Learning Systems 机器学习系统的类型
  Supervised/Unsupervised(supervise v.监督) Learning 监督/无监督学习
  Batch(n.一批 v.分批处理) and Online Learning 批处理和在线学习
  Instance-Based Versus(与) Model-Based Learning 基于实例与基于模型的学习
Main Challenges of Machine Learning 机器学习的主要挑战
  Insufficient(sufficient a.充足的) Quantity(n.数目;大量) of Training Data 训练数据不足
  Nonrepresentative(represent v.代表) Training Data  非代表性训练数据
  Poor-Quality Data  低质量数据
  Irrelevant(relevant a.相关的;正确的;适宜的;有价值的) Features  无关的特征
  Overfitting(overfit n.过拟合) the Training Data 过拟合训练数据
  Underfitting(underfit n.欠拟合) the Training Data 欠拟合训练数据
  Stepping(step n.迈步;脚步;梯级;台阶;步骤;措施;阶段;进程 v.跨步走;(短距离)移动;行走) Back 退一步? 
Testing and Validating(validate v.批准;证实;确认……有效) 测试和验证
  Hyperparameter(parameter n.界限;范围;参数;变量) Tuning(tune n.曲调;歌曲 v.调整;校音) and Model Selection 超参数调优和模型选择
  Data Mismatch(match n.比赛;对手;配偶;婚姻 v.比得上;使相配)  数据不匹配
Exercises

The Machine Learning Landscape

  With Early Release ebooks, you get books in their earliest form-the author's raw and unedited content as he or she writes--so youcan take advantage of these technologies long before the officialrelease of these titles. The following will be Chapter 1 in the finalrelease of the book.

  When most people hear “Machine Learning they picture a robot: a dependable butler or a deadly Terminator depending on who you ask. But Machine Learning is notjust a futuristic fantasy, it's already here. In fact, it has been around for decades insome specialized applications, such as Optical Character Recognition (OCR). But thefirst ML application that really became mainstream, improving the lives of hundredsof millions of people, took over the world back in the 1990s: it was the spam filterNot exactly a self-aware Skynet, but it does technically qualify as Machine Learning(it has actually learned so well that you seldom need to flag an email as spam anymore). It was followed by hundreds of Ml applications that now quietly power hun-dreds of products and features that you use regularly, from better recommendationsto voice search.