【课程笔记】李宏毅机器学习[6]：Deep Learning

本系列课程笔记为李宏毅2017,秋，台湾大学课程。
视频网址链接：https://www.bilibili.com/video/av15889450?p=10
更新日期：20200205

Deep Learning发展

• 1958: Perceptron(linear model)
• 1969: Perceptron has limitation
• 1980s: Multi-layer perceptron
  – Do not have significant difference from DNN today
• 1986: Backpropagation
  – Usually more than 3 hidden layers is not helpful
• 1989: 1 hidden layer is “good enough”, why deep?
• 2006： RBM initialization(breakthrough)
• 2009: GPU
  
  Deep = Many hidden layers

deep learning学习资源