深度学习的发展趋势
- 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
- 2011: Start to be popular in speech recognition
- 2012: win ILSVRC image competition 感知机(Perceptron)非常像我们的逻辑回归(Logistics Regression)只不过是没有sigmoid激活函数。09年的GPU的发展是很关键的,使用GPU矩阵运算节省了很多的时间。
深度学习的三个步骤
- Step1:模型选择–神经网络(Neural network)
- Step2:模型评估(Goodness of function)
- Step3:选择最优函数(Pick best function)