能否提供一个用Python实现的基于多层感知机（Multilayer Perceptron）的简单趣味实验代码示例？

当然可以。这里是一个简单的多层感知机（MLP）模型在Python中使用Keras库实现的示例，用于手写数字识别。我们将使用经典的MNIST数据集：

# 导入所需库
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.utils import to_categorical

# 加载并预处理MNIST数据
def load_data():
    (train_images, train_labels), (test_images, test_labels) = mnist.load_data()
    # 归一化到0-1范围
    train_images, test_images = train_images / 255.0, test_images / 255.0
    # 将标签转换为独热编码
    train_labels, test_labels = to_categorical(train_labels), to_categorical(test_labels)
    return (train_images, train_labels), (test_images, test_labels)

# 创建MLP模型
def create_model(input_shape):
    model = Sequential([
        Dense(128, activation='relu', input_shape=input_shape),
        Dense(64, activation='relu'),
        Dense(10, activation='softmax')  # 输出层有10个节点，对应0-9的手写数字
    ])
    return model

# 编译模型
def compile_model(model):
    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

# 训练模型
def train_model(model, train_data, epochs=10):
    train_images, train_labels = train_data
    model.fit(train_images, train_labels, epochs=epochs)

# 测试模型
def evaluate_model(model, test_data):
    test_images, test_labels = test_data
    _, accuracy = model.evaluate(test_images, test_labels)
    print(f"Test Accuracy: {accuracy * 100:.2f}%")

# 主函数
if __name__ == "__main__":
    (train_data, _), (test_data, _) = load_data()
    model = create_model(train_data[0].shape[1:])
    compile_model(model)
    train_model(model, train_data)
    evaluate_model(model, test_data)