# 模型

- [计算图](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/ji-suan-tu.md): 如何用DL4J计算图构造复杂网络。
- [多层网络](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/duo-ceng-wang-luo.md): 简单和序列网络配置。
- [循环神经网络](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/xun-huan-shen-jing-wang-luo.md): 循环神经网络在DL4J中的实现。
- [层](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/ceng.md): 已支持的神经网络层
- [顶点](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/ding-dian.md): 高级配置的计算图节点。
- [迭代器](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/die-dai-qi.md): 用于加载到神经网络的数据迭代工具。
- [监听器](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/jian-ting-qi.md): 在DL4J模型上添加钩子和监听器。
- [自定义层](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/zi-ding-yi-ceng.md): 为自定义层扩展DL4J功能。
- [模型持久化](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/mo-xing-chi-jiu-hua.md): 神经网络的存储与加载。
- [动物园用法](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/dong-wu-yuan-yong-fa.md): 为开箱即用应用程序预先构建的模型架构和权重。
- [激活](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/ji-huo.md): 梯度下降的特殊算法。
- [更新器](https://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing/geng-xin-qi.md): 梯度下降的特殊算法。


---

# 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://deeplearning4j.konduit.ai/zhong-wen-v1.0.0/mo-xing.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.