您的位置: 首页  >  IT文章  >  李宏毅机器学习

李宏毅机器学习

分类: IT文章 • 2023-11-27 08:34:31

ML Lecture 0: Introduction of Machine Learning

  1. AI v.s. ML v.s. DL
  • Artificial intelligence -> objective
  • Machine learning -> methods
  • Deep learning -> one method of machine learning
  • Hand-crafted rules
    • many "ifs"
    • hard to consider all possibilities
    • no learning (limited)
    • lots of human efforts (not suitable for small industry)
  • Machine learning
    • write programs for learning
    • looking for a function from data
      • 1. defining a set of functions -> model
      • 2. training data -> evaluate the goodness of functions (supervised learning)
      • 3. picking the best function f star
      • 4. using f star
    • 1-3 -> traing 4 -> testing
  • Learning map
    • 李宏毅机器学习
  • Regression (output: scalar/value/real number)
    • e.g. prediction of PM2.5
  • Classification  
    • binary classification (e.g. spam filtering)
    • multi-class classification (e.g. document classification)
  • Supervised learning
    • training data: input / output pair of target function (function output -> label)
    • hard to collect a large amount of labelled data -> semi-supervised learning / tramsfer learning / unsuperviesd learning / reinforcement learning
  • Structured learning - beyond classification
    • e.g. speech recognition / machine translation
  • Reinforcement learning
    • no correct answers but only critics (评价)

    • 相关推荐