基于numpy+pandas的单层神经网络

最新推荐文章于 2022-07-06 16:41:43 发布

原创

最新推荐文章于 2022-07-06 16:41:43 发布 · 747 阅读

0 ·

CC 4.0 BY-SA版权

这篇博客介绍了如何使用numpy和pandas创建一个简单的神经网络。通过初始化权重、设置超参数，如迭代次数和学习率，然后利用梯度下降更新权重，最终在测试集上计算预测准确率。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import numpy as np
from data_prep import features, targets, features_test, targets_test

def sigmoid(x):
    return 1 / (1 + np.exp(-x))
def sigmoid_prime(x):
    return sigmoid(x) * (1 - sigmoid(x))
np.random.seed(42)

n_records, n_features = features.shape
last_loss = None

# Initialize weights
weights = np.random.normal(scale=1 / n_features**.5, size=n_features)

# Neural Network hyperparameters
epochs = 1000
learnrate = 0.5

for e in range(epochs):
    del_w = np.zeros(weights.shape)
    for x, y in zip(features.values, targets):

        output = sigmoid(np.dot(weights, x))

        error = y - output
        error_term = output * (1 - output)
        del_w += error * error_term * x

    weights += learnrate * del_w / n_records

    if e % (epochs / 10) == 0:
        out = sigmoid(np.dot(features, weights))
        loss = np.mean((out - targets) ** 2)
        if last_loss and last_loss > loss: