fix URL

Author: 蔡舒起

Diff for: README.md

@@ -77,8 +77,8 @@
      - [自然语言处理与词嵌入](deep-learning/5.sequence-model-2.nlp-and-word-embeddings.md)
      - [序列模型和注意力机制](deep-learning/5.sequence-model-3.sequence-models-and-attention-machanism.md)
   6. 更多讨论（待补充）
-     1. [元学习（Meta learning）](6.meta-learning.md)
-     2. [Few-shot / Zero-shot learning](6.few-shot-learning.md)
+     1. [元学习（Meta learning）](deep-learning/6.meta-learning.md)
+     2. [Few-shot / Zero-shot learning](deep-learning/6.few-shot-learning.md)
      3. 网络压缩
 
 ### TensorFlow 
@@ -151,4 +151,4 @@ A reinforcement learning model will learn from its experience and over time will
 * 个人精力有限，欢迎感兴趣的朋友一起来完善和补充内容
 * 欢迎Star 和Share 此Repository ​
 
-[回到顶部](#深度学习机器学习学习路径)
+[回到顶部](#深度学习机器学习学习路径)