人工智能 - 第二次运行程序时精度下降 - 吾爱随笔录

我正在关注有关前馈网络的教程，并为简单的 FFN 编写了以下代码：

class FirstFFNetwork:
  
  #intialize the parameters
  def __init__(self):
    self.w1 = np.random.randn()
    self.w2 = np.random.randn()
    self.w3 = np.random.randn()
    self.w4 = np.random.randn()
    self.w5 = np.random.randn()
    self.w6 = np.random.randn()
    self.b1 = 0
    self.b2 = 0
    self.b3 = 0
  
  def sigmoid(self, x):
    return 1.0/(1.0 + np.exp(-x))
  
  def forward_pass(self, x):
    #forward pass - preactivation and activation
    self.x1, self.x2 = x
    self.a1 = self.w1*self.x1 + self.w2*self.x2 + self.b1
    self.h1 = self.sigmoid(self.a1)
    self.a2 = self.w3*self.x1 + self.w4*self.x2 + self.b2
    self.h2 = self.sigmoid(self.a2)
    self.a3 = self.w5*self.h1 + self.w6*self.h2 + self.b3
    self.h3 = self.sigmoid(self.a3)
    return self.h3
  
  def grad(self, x, y):
    #back propagation
    self.forward_pass(x)
    
    self.dw5 = (self.h3-y) * self.h3*(1-self.h3) * self.h1
    self.dw6 = (self.h3-y) * self.h3*(1-self.h3) * self.h2
    self.db3 = (self.h3-y) * self.h3*(1-self.h3)
    
    self.dw1 = (self.h3-y) * self.h3*(1-self.h3) * self.w5 * self.h1*(1-self.h1) * self.x1
    self.dw2 = (self.h3-y) * self.h3*(1-self.h3) * self.w5 * self.h1*(1-self.h1) * self.x2
    self.db1 = (self.h3-y) * self.h3*(1-self.h3) * self.w5 * self.h1*(1-self.h1)
  
    self.dw3 = (self.h3-y) * self.h3*(1-self.h3) * self.w6 * self.h2*(1-self.h2) * self.x1
    self.dw4 = (self.h3-y) * self.h3*(1-self.h3) * self.w6 * self.h2*(1-self.h2) * self.x2
    self.db2 = (self.h3-y) * self.h3*(1-self.h3) * self.w6 * self.h2*(1-self.h2)
    
  
  def fit(self, X, Y, epochs=1, learning_rate=1, initialise=True, display_loss=False):
    
    # initialise w, b
    if initialise:
      self.w1 = np.random.randn()
      self.w2 = np.random.randn()
      self.w3 = np.random.randn()
      self.w4 = np.random.randn()
      self.w5 = np.random.randn()
      self.w6 = np.random.randn()
      self.b1 = 0
      self.b2 = 0
      self.b3 = 0
      
    if display_loss:
      loss = {}
    
    for i in tqdm_notebook(range(epochs), total=epochs, unit="epoch"):
      dw1, dw2, dw3, dw4, dw5, dw6, db1, db2, db3 = [0]*9
      for x, y in zip(X, Y):
        self.grad(x, y)
        dw1 += self.dw1
        dw2 += self.dw2
        dw3 += self.dw3
        dw4 += self.dw4
        dw5 += self.dw5
        dw6 += self.dw6
        db1 += self.db1
        db2 += self.db2
        db3 += self.db3
        
      m = X.shape[1]
      self.w1 -= learning_rate * dw1 / m
      self.w2 -= learning_rate * dw2 / m
      self.w3 -= learning_rate * dw3 / m
      self.w4 -= learning_rate * dw4 / m
      self.w5 -= learning_rate * dw5 / m
      self.w6 -= learning_rate * dw6 / m
      self.b1 -= learning_rate * db1 / m
      self.b2 -= learning_rate * db2 / m
      self.b3 -= learning_rate * db3 / m
      
      if display_loss:
        Y_pred = self.predict(X)
        loss[i] = mean_squared_error(Y_pred, Y)
    
    if display_loss:
      plt.plot(loss.values())
      plt.xlabel('Epochs')
      plt.ylabel('Mean Squared Error')
      plt.show()
      
  def predict(self, X):
    #predicting the results on unseen data
    Y_pred = []
    for x in X:
      y_pred = self.forward_pass(x)
      Y_pred.append(y_pred)
    return np.array(Y_pred)

数据生成如下：

data, labels = make_blobs(n_samples=1000, centers=4, n_features=2, random_state=0)
labels_orig = labels
labels = np.mod(labels_orig, 2)
X_train, X_val, Y_train, Y_val = train_test_split(data, labels, stratify=labels, random_state=0)

昨天运行程序时，我得到了大约 98% 的训练准确率和 94% 的测试准确率。但是当我今天运行它时，准确率突然下降到 60-70%。我试图对结果进行散点图，它看起来就像是一个单一的 sigmoid，而不是前馈网络。

ffn = FirstFFNetwork()
#train the model on the data
ffn.fit(X_train, Y_train, epochs=2000, learning_rate=.01, display_loss=False)
#predictions
Y_pred_train = ffn.predict(X_train)
Y_pred_binarised_train = (Y_pred_train >= 0.5).astype("int").ravel()
Y_pred_val = ffn.predict(X_val)
Y_pred_binarised_val = (Y_pred_val >= 0.5).astype("int").ravel()
accuracy_train_1 = accuracy_score(Y_pred_binarised_train, Y_train)
accuracy_val_1 = accuracy_score(Y_pred_binarised_val, Y_val)
#model performance
print("Training accuracy", round(accuracy_train_1, 2))
print("Validation accuracy", round(accuracy_val_1, 2)

我不明白这是怎么发生的，也无法弄清楚。