1958: Perceptron(Linear model)
1969: Perceptron has limitation
1980s: Multi-layer perceptron
1986: Backpropagation
1989: 1 hidden layer is "good enough",why deep?
2006: RBM initialization(breakthrough) //Restricted Boltzmann Machine
2009: GPU
2011: Start to be popular in speech recognition
2012: win ILSVRC image competition
转载请标明出处:Deep Learning Ups and Downs