李宏毅
- 2006, Restricted Boltzmann Machine. Complex. Used to initialize multi-layer perceptron (1980), to be called Deep Learning
- Network -> function set
- Deep -> many hidden layers
- 2015, Residual Net, 152 layers.
- Define the network structure <=> define a good function
- Non-deep model -> deep model <=> feature engineering -> network design. 換句話說，如果問題能很容易地抽象feature，不像video或者audio的問題中，那麼可能deep model不一定是個好的選擇。