diff --git a/README.md b/README.md
index bf554da..7f1142a 100644
--- a/README.md
+++ b/README.md
@@ -46,7 +46,9 @@ git pull upstream master
 1. [交通事故理赔审核预测](report_01_accident_claims/README.md)
 2. [Titanic](report_02_Titanic/README.md)
 3. [Fashion](report_03_Fashion/README.md)
-3. [Tetris](report_04_Tetris/README.md)
+4. [Tetris](report_04_Tetris/README.md)
+5. [Jigsaw-Puzzle](report_05_Jigsaw-Puzzle)
+6. [Sudoku](report_06_Sudoku)
 
 
 
diff --git a/report_05_Jigsaw-Puzzle/.ipynb_checkpoints/report_template-checkpoint.ipynb b/report_05_Jigsaw-Puzzle/.ipynb_checkpoints/report_template-checkpoint.ipynb
new file mode 100644
index 0000000..1db93a2
--- /dev/null
+++ b/report_05_Jigsaw-Puzzle/.ipynb_checkpoints/report_template-checkpoint.ipynb
@@ -0,0 +1,58 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Report - 报告题目\n",
+    "\n",
+    "* 姓名\n",
+    "* 学号\n",
+    "\n",
+    "\n",
+    "## 任务简介\n",
+    "\n",
+    "这里简述一下任务是什么；最终的目标是什么\n",
+    "\n",
+    "## 解决途径\n",
+    "\n",
+    "主要包括：\n",
+    "1. 问题的思考，整体的思路\n",
+    "2. 选用的方法，以及为何选用这些方法\n",
+    "3. 所用方法的详细解释，包括理论上的背景、模型、实现的细节\n",
+    "3. 实现过程遇到的问题，以及如何解决的\n",
+    "4. 最终的结果，实验分析\n",
+    "\n",
+    "要求：\n",
+    "1. 数据的基本情况介绍\n",
+    "2. 程序，以及各个部分的解释、说明\n",
+    "3. 结果的可视化，精度等的分析\n",
+    "\n",
+    "## 总结\n",
+    "总结任务实现过程所取得的心得等。"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.9"
+  },
+  "main_language": "python"
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/report_05_Jigsaw-Puzzle/README.md b/report_05_Jigsaw-Puzzle/README.md
new file mode 100644
index 0000000..c01997a
--- /dev/null
+++ b/report_05_Jigsaw-Puzzle/README.md
@@ -0,0 +1,39 @@
+# Report5 - 拼图游戏
+
+## 任务介绍
+拼图游戏是广受欢迎的一种智力游戏，它的变化多端，难度不一。拼图游戏也有置换不变性，不管拼图的顺序是什么，输出总是固定的。下面是一个2x2的网格难题的例子，我们将在这个项目中尝试解决它。
+
+![Jigsaw-Puzzle_demo1.png](images/Jigsaw-Puzzle_demo1.png)
+
+解决一个3x3网格的难题是极其困难的。下面是这些谜题的可能组合。
+
+```
+2x2 puzzle = 4! = 24 combinations 
+3x3 puzzle = 9! = 362880 comb'ns
+```
+
+为了解决一个3x3的难题，网络必须从362880中预测出一个正确的组合。这也是为什么3x3拼图是一个难题的另一个原因。
+
+为了让大家学习如何使用卷积神经网络，首先尝试解决一个2x2的拼图游戏。
+
+## 数据
+这个数据集包含2x2和3x3的puzzle。你可以在这里找到它。
+
+https://www.kaggle.com/shivajbd/jigsawpuzzle
+
+下面是一个2x2网格拼图的数据示例。输入是一个200x200像素的图像和标签是一个4个整数的数组，其中每个整数告诉每个片段的正确位置。
+
+![Jigsaw-Puzzle_sample-data](images/Jigsaw-Puzzle_sample-data.png)
+
+## 要求
+
+1. 分析拼图游戏的特点，设计实现的方法
+2. 在Kaggle网站上，下载数据
+3. 编写神经网络代码，测试自己算法的效果如何
+4. 测试所研究方法的效果
+5. 分析自己实现的方法的问题，以及如何改进
+6. 深入思考，如何解决3x3的拼图？或者更大的拼图？
+7. 按照`report_template.ipynb`撰写自己的报告。
+
+## References
+* https://www.kaggle.com/shivajbd/jigsawpuzzle
\ No newline at end of file
diff --git a/report_05_Jigsaw-Puzzle/images/Jigsaw-Puzzle_demo1.png b/report_05_Jigsaw-Puzzle/images/Jigsaw-Puzzle_demo1.png
new file mode 100644
index 0000000..85faf1d
Binary files /dev/null and b/report_05_Jigsaw-Puzzle/images/Jigsaw-Puzzle_demo1.png differ
diff --git a/report_05_Jigsaw-Puzzle/images/Jigsaw-Puzzle_results.png b/report_05_Jigsaw-Puzzle/images/Jigsaw-Puzzle_results.png
new file mode 100644
index 0000000..0438c28
Binary files /dev/null and b/report_05_Jigsaw-Puzzle/images/Jigsaw-Puzzle_results.png differ
diff --git a/report_05_Jigsaw-Puzzle/images/Jigsaw-Puzzle_sample-data.png b/report_05_Jigsaw-Puzzle/images/Jigsaw-Puzzle_sample-data.png
new file mode 100644
index 0000000..28e4fde
Binary files /dev/null and b/report_05_Jigsaw-Puzzle/images/Jigsaw-Puzzle_sample-data.png differ
diff --git a/report_05_Jigsaw-Puzzle/report_template.ipynb b/report_05_Jigsaw-Puzzle/report_template.ipynb
new file mode 100644
index 0000000..1db93a2
--- /dev/null
+++ b/report_05_Jigsaw-Puzzle/report_template.ipynb
@@ -0,0 +1,58 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Report - 报告题目\n",
+    "\n",
+    "* 姓名\n",
+    "* 学号\n",
+    "\n",
+    "\n",
+    "## 任务简介\n",
+    "\n",
+    "这里简述一下任务是什么；最终的目标是什么\n",
+    "\n",
+    "## 解决途径\n",
+    "\n",
+    "主要包括：\n",
+    "1. 问题的思考，整体的思路\n",
+    "2. 选用的方法，以及为何选用这些方法\n",
+    "3. 所用方法的详细解释，包括理论上的背景、模型、实现的细节\n",
+    "3. 实现过程遇到的问题，以及如何解决的\n",
+    "4. 最终的结果，实验分析\n",
+    "\n",
+    "要求：\n",
+    "1. 数据的基本情况介绍\n",
+    "2. 程序，以及各个部分的解释、说明\n",
+    "3. 结果的可视化，精度等的分析\n",
+    "\n",
+    "## 总结\n",
+    "总结任务实现过程所取得的心得等。"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.9"
+  },
+  "main_language": "python"
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/report_06_Sudoku/.ipynb_checkpoints/report_template-checkpoint.ipynb b/report_06_Sudoku/.ipynb_checkpoints/report_template-checkpoint.ipynb
new file mode 100644
index 0000000..1db93a2
--- /dev/null
+++ b/report_06_Sudoku/.ipynb_checkpoints/report_template-checkpoint.ipynb
@@ -0,0 +1,58 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Report - 报告题目\n",
+    "\n",
+    "* 姓名\n",
+    "* 学号\n",
+    "\n",
+    "\n",
+    "## 任务简介\n",
+    "\n",
+    "这里简述一下任务是什么；最终的目标是什么\n",
+    "\n",
+    "## 解决途径\n",
+    "\n",
+    "主要包括：\n",
+    "1. 问题的思考，整体的思路\n",
+    "2. 选用的方法，以及为何选用这些方法\n",
+    "3. 所用方法的详细解释，包括理论上的背景、模型、实现的细节\n",
+    "3. 实现过程遇到的问题，以及如何解决的\n",
+    "4. 最终的结果，实验分析\n",
+    "\n",
+    "要求：\n",
+    "1. 数据的基本情况介绍\n",
+    "2. 程序，以及各个部分的解释、说明\n",
+    "3. 结果的可视化，精度等的分析\n",
+    "\n",
+    "## 总结\n",
+    "总结任务实现过程所取得的心得等。"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.9"
+  },
+  "main_language": "python"
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/report_06_Sudoku/README.md b/report_06_Sudoku/README.md
new file mode 100644
index 0000000..ed1c79c
--- /dev/null
+++ b/report_06_Sudoku/README.md
@@ -0,0 +1,57 @@
+# Report6 - 数独
+
+## 内容
+数独（shù dú, Sudoku）是源自18世纪[瑞士](https://baike.baidu.com/item/瑞士/131482)的一种数学游戏。是一种运用纸、笔进行演算的[逻辑游戏](https://baike.baidu.com/item/逻辑游戏/12814189)。玩家需要根据9×9盘面上的已知数字，推理出所有剩余空格的数字，并满足每一行、每一列、每一个粗线宫（3*3）内的数字均含1-9，不重复。
+
+数独盘面是个九宫，每一宫又分为九个小格。在这八十一格中给出一定的已知数字和解题条件，利用逻辑和推理，在其他的空格上填入1-9的数字。使1-9每个数字在每一行、每一列和每一宫中都只出现一次，所以又称“九宫格”。
+
+![sudoku_1.jpeg](images/sudoku_1.jpeg)
+
+是否可以用卷积神经网络(CNN)解决数独问题。数独有空间特征，因为它有特殊的数字排列，而CNN擅长提取空间特征，尝试使用CNN来求解数独。
+
+
+
+## 数据
+这个数据集包含了1百万数独的数据，你可以在这里找到它。
+
+https://www.kaggle.com/bryanpark/sudoku
+
+
+
+示例的数据如下所示
+
+![sudoku_data.png](images/sudoku_data.png)
+
+
+
+数据集包含2列。`quizzes`栏目是未解的游戏，`solutions`栏目各自的已解游戏。每场比赛都由81个数字组成的字符串表示。以下是从字符串转换而来的9x9数独。数字0代表未解游戏中的空白位置。
+
+```
+[[0 0 4 3 0 0 2 0 9]
+ [0 0 5 0 0 9 0 0 1]
+ [0 7 0 0 6 0 0 4 3]
+ [0 0 6 0 0 2 0 8 7]
+ [1 9 0 0 0 7 4 0 0]
+ [0 5 0 0 8 3 0 0 0]
+ [6 0 0 0 0 0 1 0 5]
+ [0 0 3 5 0 8 6 9 0]
+ [0 4 2 9 1 0 3 0 0]]
+```
+
+
+
+## 要求
+
+1. 分析数独游戏的特点，设计实现的方法
+2. 在Kaggle网站上，下载数据
+3. 编写神经网络代码，测试自己算法的效果如何
+4. 测试所研究方法的效果
+5. 分析自己实现的方法的问题，以及如何改进
+6. 深入思考，如何使用强化学习的方法实现求解数独问题？
+7. 按照`report_template.ipynb`撰写自己的报告。
+
+
+
+## References
+
+* https://www.kaggle.com/bryanpark/sudoku
\ No newline at end of file
diff --git a/report_06_Sudoku/images/sudoku_1.jpeg b/report_06_Sudoku/images/sudoku_1.jpeg
new file mode 100644
index 0000000..75c538d
Binary files /dev/null and b/report_06_Sudoku/images/sudoku_1.jpeg differ
diff --git a/report_06_Sudoku/images/sudoku_data.png b/report_06_Sudoku/images/sudoku_data.png
new file mode 100644
index 0000000..03a5091
Binary files /dev/null and b/report_06_Sudoku/images/sudoku_data.png differ
diff --git a/report_06_Sudoku/report_template.ipynb b/report_06_Sudoku/report_template.ipynb
new file mode 100644
index 0000000..1db93a2
--- /dev/null
+++ b/report_06_Sudoku/report_template.ipynb
@@ -0,0 +1,58 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Report - 报告题目\n",
+    "\n",
+    "* 姓名\n",
+    "* 学号\n",
+    "\n",
+    "\n",
+    "## 任务简介\n",
+    "\n",
+    "这里简述一下任务是什么；最终的目标是什么\n",
+    "\n",
+    "## 解决途径\n",
+    "\n",
+    "主要包括：\n",
+    "1. 问题的思考，整体的思路\n",
+    "2. 选用的方法，以及为何选用这些方法\n",
+    "3. 所用方法的详细解释，包括理论上的背景、模型、实现的细节\n",
+    "3. 实现过程遇到的问题，以及如何解决的\n",
+    "4. 最终的结果，实验分析\n",
+    "\n",
+    "要求：\n",
+    "1. 数据的基本情况介绍\n",
+    "2. 程序，以及各个部分的解释、说明\n",
+    "3. 结果的可视化，精度等的分析\n",
+    "\n",
+    "## 总结\n",
+    "总结任务实现过程所取得的心得等。"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.9"
+  },
+  "main_language": "python"
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}