LSTM 基础

Lesson Overview

In "Machine Learning for Trading" → "LSTM 预测", this lesson "LSTM 基础" builds knowledge you can apply immediately.

LSTM以序列输入和隐藏状态表示历史。张量常为样本×时间×特征，但框架约定需明确；打乱训练样本不等于允许随机混合时间测试。 核batch_first→在各段内部建20步窗口→训练段拟合尺度→输入3特征/hidden8→运行8轮并记录形状与损失。 本课作业：配套训练输入139×20×3，各维是什么？测试窗口能否包含训练后尚未确认的未来标签？

Core Concepts

These points align with the video walkthrough—take notes as you watch.

• ▸LSTM以序列输入和隐藏状态表示历史。张量常为样本×时间×特征，但框架约定需明确；打乱训练样本不等于允许随机混合时间测试。
• ▸核batch_first→在各段内部建20步窗口→训练段拟合尺度→输入3特征/hidden8→运行8轮并记录形状与损失。
• ▸本课作业：配套训练输入139×20×3，各维是什么？测试窗口能否包含训练后尚未确认的未来标签？

Practical Application

After studying, complete the companion practice lesson to move from understanding to doing.

• ▸Follow along in Jupyter or VS Code
• ▸Log how parameter changes affect backtest results
• ▸Submit a reproducible analysis notebook

FAQ

• ▸Q: How does this lesson fit the course? A: Part of "LSTM 预测"—follow the curriculum order.
• ▸Q: What do I need? A: Demo account and notes; quant lessons need a Python environment.
• ▸Q: How do I know I've mastered it? A: Pass the quiz and explain three key points of LSTM 基础 on your own.