我正在课堂上学习感知器以及如何使用反向传播来训练模型。我目前在实现方面遇到了麻烦，因为它只为我提供了 50% 的数据准确率，而我班上的大多数其他人都获得了 90% 的准确率。在我的实施中是否有什么我忽略的事情？这是我迄今为止从我所查看的来源中获得的信息。
class Perceptron():
def __init__(self, num_features):
self.num_features = num_features
self.weights = np.random.rand(num_features) * 0.1 # This makes an array filled w/ zeros with the shape of num_features
self.bias = 0.0
def forward(self, x):
linear = np.dot(x, self.weights) + self.bias
print(linear)
predictions = np.where(linear > 0, 1, 0)
return predictions
def backward(self, x, y, predictions):
errors = y - predictions
self.weights += self.learning_rate * np.dot(x.T, errors)
self.bias += self.learning_rate * np.sum(errors)
return errors
def train(self, x, y, epochs, learning_rate = 0.01):
self.learning_rate = learning_rate
for e in range(epochs):
for i in range(y.shape[0]):
x_i, y_i = x[i], y[i]
prediction = self.forward(x_i)
self.backward(x_i, y_i, prediction)
def evaluate(self, x, y):
predictions = self.forward(x)
accuracy = np.mean(predictions == y)
return accuracy
到目前为止，我已经尝试了不同的学习率并询问了班上的其他人，说实话，这并没有真正改变我的实施结果。我预计准确率约为 90%，但我只得到 50% 的准确率。
编辑：这是一些示例数据：
0.77 -1.14 0
-0.33 1.44 0
0.91 -3.07 0
-0.37 -1.91 0
-1.84 -1.13 0
-1.50 0.34 0
-0.63 -1.53 0
-1.08 -1.23 0
0.39 -1.99 0
-1.26 -2.90 0
-5.27 -0.78 0
-0.49 -2.74 0
1.48 -3.74 0
-1.64 -1.96 0
0.45 0.36 0
-1.48 -1.17 0
-2.94 -4.47 0
-2.19 -1.48 0
0.02 -0.02 0
-2.24 -2.12 0
-3.17 -3.69 0
-4.09 1.03 0
-2.41 -2.31 0
-3.45 -0.61 0
-3.96 -2.00 0
-2.95 -1.16 0
-2.42 -3.35 0
-1.74 -1.10 0
-1.61 -1.28 0
-2.59 -2.21 0
-2.64 -2.20 0
-2.84 -4.12 0
-1.45 -2.26 0
-3.98 -1.05 0
-2.97 -1.63 0
-0.68 -1.52 0
-0.10 -3.43 0
-1.14 -2.66 0
-2.92 -2.51 0
-2.14 -1.62 0
-3.33 -0.44 0
-1.05 -3.85 0
0.38 0.95 0
-0.05 -1.95 0
-3.20 -0.22 0
-2.26 0.01 0
-1.41 -0.33 0
-1.20 -0.71 0
-1.69 0.80 0
-1.52 -1.14 0
3.88 0.65 1
0.73 2.97 1
0.83 3.94 1
1.59 1.25 1
3.92 3.48 1
3.87 2.91 1
1.14 3.91 1
1.73 2.80 1
2.95 1.84 1
2.61 2.92 1
2.38 0.90 1
2.30 3.33 1
1.31 1.85 1
1.56 3.85 1
2.67 2.41 1
1.23 2.54 1
1.33 2.03 1
1.36 2.68 1
2.58 1.79 1
2.40 0.91 1
0.51 2.44 1
2.17 2.64 1
4.38 2.94 1
1.09 3.12 1
0.68 1.54 1
1.93 3.71 1
1.26 1.17 1
1.90 1.34 1
3.13 0.92 1
0.85 1.56 1
1.50 3.93 1
2.95 2.09 1
0.77 2.84 1
1.00 0.46 1
3.19 2.32 1
2.92 2.32 1
2.86 1.35 1
0.97 2.68 1
1.20 1.31 1
1.54 2.02 1
1.65 0.63 1
1.36 -0.22 1
2.63 0.40 1
0.90 2.05 1
1.26 3.54 1
0.71 2.27 1
1.96 0.83 1
2.52 1.83 1
2.77 2.82 1
4.16 3.34 1
在使用感知器模型之前，该代码首先被随机化，然后分为两部分：2/3 的原始数据用于训练，另外 1/3 用于测试。之后，对训练和测试数据集的前 2 个特征进行 z 分数标准化。
这就是我使用该类的方式：
perceptron = Perceptron(num_features = 2)
perceptron.train(combined_x_train[:, :2], combined_x_train[:, 2], epochs = 5, learning_rate=0.1)
accuracy = perceptron.evaluate(x_train, y_train)
print(f'Final Accuracy: {accuracy * 100:.2f}%')
嘿这是我的实现：
import numpy as np
from sklearn.model_selection import train_test_split
# Sample data provided
data = np.array([
[0.77, -1.14, 0], [-0.33, 1.44, 0], [0.91, -3.07, 0], [-0.37, -1.91, 0],
[-1.84, -1.13, 0], [-1.50, 0.34, 0], [-0.63, -1.53, 0], [-1.08, -1.23, 0],
[0.39, -1.99, 0], [-1.26, -2.90, 0], [-5.27, -0.78, 0], [-0.49, -2.74, 0],
[1.48, -3.74, 0], [-1.64, -1.96, 0], [0.45, 0.36, 0], [-1.48, -1.17, 0],
[-2.94, -4.47, 0], [-2.19, -1.48, 0], [0.02, -0.02, 0], [-2.24, -2.12, 0],
[-3.17, -3.69, 0], [-4.09, 1.03, 0], [-2.41, -2.31, 0], [-3.45, -0.61, 0],
[-3.96, -2.00, 0], [-2.95, -1.16, 0], [-2.42, -3.35, 0], [-1.74, -1.10, 0],
[-1.61, -1.28, 0], [-2.59, -2.21, 0], [-2.64, -2.20, 0], [-2.84, -4.12, 0],
[-1.45, -2.26, 0], [-3.98, -1.05, 0], [-2.97, -1.63, 0], [-0.68, -1.52, 0],
[-0.10, -3.43, 0], [-1.14, -2.66, 0], [-2.92, -2.51, 0], [-2.14, -1.62, 0],
[-3.33, -0.44, 0], [-1.05, -3.85, 0], [0.38, 0.95, 0], [-0.05, -1.95, 0],
[-3.20, -0.22, 0], [-2.26, 0.01, 0], [-1.41, -0.33, 0], [-1.20, -0.71, 0],
[-1.69, 0.80, 0], [-1.52, -1.14, 0], [3.88, 0.65, 1], [0.73, 2.97, 1],
[0.83, 3.94, 1], [1.59, 1.25, 1], [3.92, 3.48, 1], [3.87, 2.91, 1],
[1.14, 3.91, 1], [1.73, 2.80, 1], [2.95, 1.84, 1], [2.61, 2.92, 1],
[2.38, 0.90, 1], [2.30, 3.33, 1], [1.31, 1.85, 1], [1.56, 3.85, 1],
[2.67, 2.41, 1], [1.23, 2.54, 1], [1.33, 2.03, 1], [1.36, 2.68, 1],
[2.58, 1.79, 1], [2.40, 0.91, 1], [0.51, 2.44, 1], [2.17, 2.64, 1],
[4.38, 2.94, 1], [1.09, 3.12, 1], [0.68, 1.54, 1], [1.93, 3.71, 1],
[1.26, 1.17, 1], [1.90, 1.34, 1], [3.13, 0.92, 1], [0.85, 1.56, 1],
[1.50, 3.93, 1], [2.95, 2.09, 1], [0.77, 2.84, 1], [1.00, 0.46, 1],
[3.19, 2.32, 1], [2.92, 2.32, 1], [2.86, 1.35, 1], [0.97, 2.68, 1],
[1.20, 1.31, 1], [1.54, 2.02, 1], [1.65, 0.63, 1], [1.36, -0.22, 1],
[2.63, 0.40, 1], [0.90, 2.05, 1], [1.26, 3.54, 1], [0.71, 2.27, 1],
[1.96, 0.83, 1], [2.52, 1.83, 1], [2.77, 2.82, 1], [4.16, 3.34, 1]
])
# Split data into features (X) and labels (y)
X = data[:, :2]
y = data[:, 2]
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
# Perceptron class definition
class Perceptron():
def __init__(self, num_features):
self.num_features = num_features
self.weights = np.random.rand(num_features) * 0.1 # Small random weights initialization
self.bias = 0.0
def forward(self, x):
# Compute the linear output and apply step function
linear = np.dot(x, self.weights) + self.bias
predictions = np.where(linear > 0, 1, 0)
return predictions
def backward(self, x, y, predictions):
# Calculate the error
errors = y - predictions
# Update weights and bias using the perceptron rule
self.weights += self.learning_rate * np.dot(x.T, errors)
self.bias += self.learning_rate * np.sum(errors)
return errors
def train(self, x, y, epochs, learning_rate=0.01):
self.learning_rate = learning_rate
for e in range(epochs):
# Calculate predictions for entire batch
predictions = self.forward(x)
# Update weights and bias after processing the entire batch
self.backward(x, y, predictions)
def evaluate(self, x, y):
# Predict on the test data
predictions = self.forward(x)
# Calculate accuracy
accuracy = np.mean(predictions == y)
return accuracy
# Using the Perceptron class
perceptron = Perceptron(num_features=2)
perceptron.train(X_train, y_train, epochs=100, learning_rate=0.01)
accuracy = perceptron.evaluate(X_test, y_test)
accuracy_train = perceptron.evaluate(X_train, y_train)
# final result
accuracy, accuracy_train
我在调用函数之前使用train_test_split来快速测试它。 以下是我在您的代码中发现的一些错误：