diff --git a/README.md b/README.md
index c60ab11..c20b0f4 100644
--- a/README.md
+++ b/README.md
@@ -46,14 +46,13 @@
 
 ![SOM Algorithm](./images/SOM2.png)
 
-### 참고[¶]()
 
-[https://untitledtblog.tistory.com/5](https://untitledtblog.tistory.com/5)
 
 ### SOM 예제 코드 1[¶]()
 
 <details>
 <summary>Code View</summary>
+
 <summary>입력 데이터 생성</summary>
 <div markdown="1">
   
@@ -264,6 +263,7 @@ array(\[\[0.76959259, 0.03105338\],
 
 <details>
 <summary>Code View</summary>
+
 <summary>Randomize 함수</summary>
 <div markdown="1">
   
@@ -404,9 +404,102 @@ array(\[\[0.76959259, 0.03105338\],
 
 </div>
 
+<summary>결과</summary>
+<div markdown="1">
+
+![result1](./images/a1.png)
+![result2](./images/a2.png)
+
+</div>
+
 </details>
 
 
+### SOM 예제 코드 3[¶]()
+
+<details>
+<summary>Code View</summary>
+<div markdown="1">
+  
+````python
+    import os
+    import logging
+    import numpy as np
+    import matplotlib.pyplot as plt
+    import matplotlib.font_manager as fm
+    import matplotlib as mpl
+
+    # 마이너스 기호 표시 설정
+    mpl.rcParams['axes.unicode_minus'] = False
+
+    # 한글 폰트 설정 - Windows
+    # font_location = fm.findfont(fm.FontProperties(family='Malgun Gothic'))
+    # fm.FontProperties(fname=font_location)
+    # plt.rcParams['font.family'] = 'Malgun Gothic'
+
+    # 로거 수준을 ERROR로 설정하여 경고 메시지를 제거
+    matplotlib_logger = logging.getLogger("matplotlib")
+    matplotlib_logger.setLevel(logging.ERROR)
+    # 한글 폰트 설정 - Linux
+    font_dir = "/usr/share/fonts/truetype/nanum"
+    nanum_gothic_ttf = os.path.join(font_dir, "NanumGothic.ttf")
+    nanum_gothic = fm.FontProperties(fname=nanum_gothic_ttf)
+    # plt.rcParams["font.family"] = nanum_gothic.get_name()
+    plt.rcParams["axes.unicode_minus"] = False
+
+    # 초기 연결 가중치 개수
+    num_rows = 15
+    num_cols = 15
+    a = 0.20  # 이웃 크기(G)와 학습률(eta)의 감소를 위한 인자
+
+    # 초기 가중치 값 설정
+    dx = 0.1
+    m = dx * (1 - 2 * np.random.rand(num_rows, num_cols)) + dx * (1j - 2j * np.random.rand(num_rows, num_cols))
+
+    for cycle in range(1, 5001):
+        eta = cycle ** (-a)
+        G = 0.5 + 10 * cycle ** (-a)  # 가우시안 폭 관련 파라미터
+        x = 1 - 2 * np.random.rand()
+        y = 1 - 2 * np.random.rand()
+
+        inp = x + y * 1j  # 입력 데이터(복소수로 2차원 표현)
+
+        dist_mat = (np.real(m) - np.real(inp)) ** 2 + (np.imag(m) - np.imag(inp)) ** 2
+        win_rows, win_cols = np.unravel_index(np.argmin(dist_mat, axis=None), dist_mat.shape)
+
+        col_idx, row_idx = np.meshgrid(range(1, num_cols + 1), range(1, num_rows + 1))
+        grid_dist = np.abs(row_idx - win_rows) + np.abs(col_idx - win_cols)
+        f = eta * np.exp(-(grid_dist / G) ** 2)
+
+        if cycle in [1, 10, 30, 50, 100, 200, 400, 600, 800, 1000, 3000, 5000]:
+            plt.clf()
+            plt.plot(np.real(m), np.imag(m), 'w-', np.real(m.T), np.imag(m.T), 'w-')
+            plt.gca().set_facecolor('k')
+            plt.title('훈련 횟수: {}, 이웃의 크기: {:.2f}, 학습률: {:.2f}'.format(cycle, G, eta), fontproperties=nanum_gothic)
+            plt.draw()
+            plt.pause(0.001)
+
+        m = m + f * (inp - m)
+
+    plt.show()
+
+````
+
+</div>
+
+<summary>결과</summary>
+<div markdown="1">
+
+![result1](./images/b1.png)
+![result2](./images/b2.png)
+![result3](./images/b3.png)
+
+</div>
+<details>
+
+
 ### 참고[¶]()
 
+- 머신러닝 프로그래밍 과목, 김성수 교수
+- [https://untitledtblog.tistory.com/5](https://untitledtblog.tistory.com/5)
 - ChatGPT
\ No newline at end of file