# 第三周 序列模型和注意力机制（Sequence models & Attention mechanism）

- [3.1 基础模型（Basic Models）](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/31-ji-chu-mo-xing-ff08-basic-models.md)
- [3.2 选择最可能的句子（Picking the most likely sentence）](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/32-xuan-ze-zuike-neng-de-ju-zi-ff08-picking-the-most-likely-sentence.md)
- [3.3 集束搜索（Beam Search）](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/33-ji-shu-sou-suo-ff08-beam-search.md)
- [3.4 改进集束搜索（Refinements to Beam Search）](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/34-gai-jin-ji-shu-sou-suo-ff08-refinements-to-beam-search.md)
- [3.5 集束搜索的误差分析（Error analysis in beam search）](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/35-ji-shu-sou-suode-wu-cha-fen-xi-ff08-error-analysis-in-beam-search.md)
- [3.6 Bleu 得分（选修）（Bleu Score (optional)）](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/36-bleu-de-fen-ff08-xuan-xiu-ff09-ff08-bleu-score-optional.md)
- [3.7 注意力模型直观理解（Attention Model Intuition）](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/37-zhu-yi-li-mo-xing-zhi-guan-li-jie-ff08-attention-model-intuition.md)
- [3.8注意力模型（Attention Model）](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/38zhu-yi-li-mo-xing-ff08-attention-model.md)
- [3.9语音识别（Speech recognition）](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/39yu-yin-shi-bieff08-speech-recognition.md)
- [3.10触发字检测（Trigger Word Detection）](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/310hong-fa-zi-jian-ce-ff08-trigger-word-detection.md)
- [Neural machine translation with attention](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/neural-machine-translation-with-attention-v4.md)
- [nmt\_utils.py](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/nmtutils-py.md)
- [Trigger word detection](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/trigger-word-detection-v1.md)
- [td\_utils.py](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism/tdutils-py.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/di-san-zhou-xu-lie-mo-xing-he-zhu-yi-li-ji-zhi-ff08-sequence-models-and-attention-mechanism.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.