[3.1 线性回归](3.1%E7%BA%BF%E6%80%A7%E5%9B%9E%E5%BD%92.md) [3.2 线性回归的从零开始实现](3.2%E7%BA%BF%E6%80%A7%E5%9B%9E%E5%BD%92%E7%9A%84%E4%BB%8E%E9%9B%B6%E5%BC%80%E5%A7%8B%E5%AE%9E%E7%8E%B0.md) [3.3 线性回归的简洁实现](3.3%E7%BA%BF%E6%80%A7%E5%9B%9E%E5%BD%92%E7%9A%84%E7%AE%80%E6%B4%81%E5%AE%9E%E7%8E%B0.md) [3.4 softmax回归](3.4softmax%E5%9B%9E%E5%BD%92.md) [3.5 图像分类数据集（Fashion-MINST）](3.5%E5%9B%BE%E5%83%8F%E5%88%86%E7%B1%BB%E6%95%B0%E6%8D%AE%E9%9B%86%EF%BC%88Fashion-MINST%EF%BC%89.md) [3.6 softmax回归的从零开始实现](3.6softmax%E5%9B%9E%E5%BD%92%E7%9A%84%E4%BB%8E%E9%9B%B6%E5%BC%80%E5%A7%8B%E5%AE%9E%E7%8E%B0.md) [3.7 softmax回归的简洁实现](3.7softmax%E5%9B%9E%E5%BD%92%E7%9A%84%E7%AE%80%E6%B4%81%E5%AE%9E%E7%8E%B0.md) [3.8 多层感知机](3.8%E5%A4%9A%E5%B1%82%E6%84%9F%E7%9F%A5%E6%9C%BA.md) [3.9 多层感知机的从零开始实现](3.9%E5%A4%9A%E5%B1%82%E6%84%9F%E7%9F%A5%E6%9C%BA%E7%9A%84%E4%BB%8E%E9%9B%B6%E5%BC%80%E5%A7%8B%E5%AE%9E%E7%8E%B0.md) [3.10 多层感知机的简洁实现](3.10%E5%A4%9A%E5%B1%82%E6%84%9F%E7%9F%A5%E6%9C%BA%E7%9A%84%E7%AE%80%E6%B4%81%E5%AE%9E%E7%8E%B0.md) [3.11 模型选择、反向传播和计算图](3.11%E6%A8%A1%E5%9E%8B%E9%80%89%E6%8B%A9%E3%80%81%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD%E5%92%8C%E8%AE%A1%E7%AE%97%E5%9B%BE.md) [3.12 权重衰减](3.12%E6%9D%83%E9%87%8D%E8%A1%B0%E5%87%8F.md) [3.13 丢弃法](3.13%E4%B8%A2%E5%BC%83%E6%B3%95.md) [3.14 正向传播、反向传播和计算图](3.14%E6%AD%A3%E5%90%91%E4%BC%A0%E6%92%AD%E3%80%81%E5%8F%8D%E5%90%91%E4%BC%A0%E6%92%AD%E5%92%8C%E8%AE%A1%E7%AE%97%E5%9B%BE.md) [3.15 数值稳定性和模型初始化](3.15%E6%95%B0%E5%80%BC%E7%A8%B3%E5%AE%9A%E6%80%A7%E5%92%8C%E6%A8%A1%E5%9E%8B%E5%88%9D%E5%A7%8B%E5%8C%96.md) [3.16 实战kaggle比赛：房价预测](3.16%E5%AE%9E%E6%88%98kaggle%E6%AF%94%E8%B5%9B%EF%BC%9A%E6%88%BF%E4%BB%B7%E9%A2%84%E6%B5%8B.md)