李宏毅机器学习-课件_22-auto.pdfVIP

Unsupervised Learning: Deep Auto-encoder Unsupervised Learning “We expect unsupervised learning to become far more important in the longer term. Human and animal learning is largely unsupervised: we discover the structure of the world by observing it, not by being told the name of every object.” – LeCun, Bengio, Hinton, Nature 2015 As Ive said in previous statements: most of human and animal learning is unsupervised learning. If intelligence was a cake, unsupervised learning would be the cake, supervised learning would be the icing on the cake, and reinforcement learning would be the cherry on the cake. We know how to make the icing and the cherry, but we dont know how to make the cake. - Yann LeCun, March 14, 2016 (Facebook) Auto-encoder Usually 784 Compact NN code representation of Encoder the input object 28 X 28 = 784 Learn together Can reconstruct NN code Decoder the original object Recap: PCA Minimize −ො 2 As close as possible encode decode ො hidden layer Input layer (linear) output layer Bottleneck later Output of the hidden layer is the code Deep Auto-encoder Symmetric is not