Auto-encoder -Pre-training DNN Greedy Layer-wise Pre-training again output 10 500 1000 a1← W2' 136JDL 合 1000 1000 合 w2 1000 1000 合 fixWi Input 784 Input 784 Auto-encoder – Pre-training DNN • Greedy Layer-wise Pre-training again Target 784 1000 1000 500 10 Input output Input 784 1000 W1 1000 1000 fix 𝑥 𝑎 1 𝑎 ො 1 W2 W2 ’