{"id":19589701,"url":"https://github.com/jackaduma/awesome_nlp-interview-notes","last_synced_at":"2026-02-25T05:35:40.000Z","repository":{"id":205050611,"uuid":"702769041","full_name":"jackaduma/awesome_NLP-Interview-Notes","owner":"jackaduma","description":"nlp_interview notes and answers: 该仓库主要记录 NLP 算法工程师相关的面试题和参考答案","archived":false,"fork":false,"pushed_at":"2023-11-16T10:16:57.000Z","size":452,"stargazers_count":22,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-11-02T15:02:57.139Z","etag":null,"topics":["ai","interview","interview-practice","interview-prep","interview-preparation","interview-questions","interviews","interviews-questions","nlp"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jackaduma.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-10-10T01:27:59.000Z","updated_at":"2025-07-17T00:02:33.000Z","dependencies_parsed_at":null,"dependency_job_id":"15882e2f-819b-4945-89ce-bbcf47aea796","html_url":"https://github.com/jackaduma/awesome_NLP-Interview-Notes","commit_stats":null,"previous_names":["jackaduma/awesome_nlp-interview-notes"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jackaduma/awesome_NLP-Interview-Notes","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackaduma%2Fawesome_NLP-Interview-Notes","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackaduma%2Fawesome_NLP-Interview-Notes/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackaduma%2Fawesome_NLP-Interview-Notes/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackaduma%2Fawesome_NLP-Interview-Notes/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jackaduma","download_url":"https://codeload.github.com/jackaduma/awesome_NLP-Interview-Notes/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jackaduma%2Fawesome_NLP-Interview-Notes/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29811574,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-25T03:30:18.102Z","status":"ssl_error","status_checked_at":"2026-02-25T03:30:17.799Z","response_time":61,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","interview","interview-practice","interview-prep","interview-preparation","interview-questions","interviews","interviews-questions","nlp"],"created_at":"2024-11-11T08:20:19.666Z","updated_at":"2026-02-25T05:35:39.971Z","avatar_url":"https://github.com/jackaduma.png","language":null,"readme":"\n# awesome_NLP-Interview-Notes\nNLP interview notes and answers\n\n## **内容说明**\n\n问题来自 [NLP 面无不过： km1994 - NLP-Interview-Notes ](https://github.com/km1994/NLP-Interview-Notes)\n\n**答案 为 自己编写，不保证正确，仅供参考。**\n\n**有些问题，提供的答案更多是一种线索，如想深入了解，请自行参考更多资料**\n\n## 更新记录\n\n1. 2023.11 发布：CNN, RNN, Attention\n\n## 目录\n\n- [x] **[3 深度学习算法篇常见面试篇](./3%20深度学习算法篇常见面试篇/)**\n  - [x] **[CNN 常见面试篇](./3%20深度学习算法篇常见面试篇/CNN%20常见面试篇.md)**\n    - [x] 一、动机篇\n    - [x] 二、CNN 卷积层篇\n      - [x] 2.1 卷积层的本质是什么？\n      - [x] 2.2 CNN 卷积层与全连接层的联系？\n      - [x] 2.3 channel的含义是什么？\n    - [x] 三、CNN 池化层篇\n      - [x] 3.1 池化层针对区域是什么？\n      - [x] 3.2 池化层的种类有哪些？\n      - [x] 3.3 池化层的作用是什么？\n      - [x] 3.4 池化层 反向传播 是什么样的？\n      - [x] 3.5 mean pooling 池化层 反向传播 是什么样的？\n      - [x] 3.6 max pooling 池化层 反向传播 是什么样的？\n    - [x] 四、CNN 整体篇\n      - [x] 4.1 CNN 的流程是什么？\n      - [x] 4.2 CNN 的特点是什么？\n      - [x] 4.3 卷积神经网络为什么会具有平移不变性？\n      - [x] 4.4 卷积神经网络中im2col是如何实现的？\n      - [x] 4.5 CNN 的局限性是什么？\n    - [x] 五、Iterated Dilated CNN 篇\n      - [x] 5.1 什么是 Dilated CNN 空洞卷积？\n      - [x] 5.2 什么是 Iterated Dilated CNN？\n    - [x] 六、反卷积 篇\n      - [x] 6.1 解释反卷积的原理和用途？\n  - [x] **[RNN 常见面试篇](./3%20深度学习算法篇常见面试篇/RNN%20常见面试篇.md)**\n    - [x] 一、RNN 篇\n      - [x] 1.2 为什么需要 RNN?\n      - [x] 1.2 RNN 结构是怎么样的？\n      - [x] 1.3 RNN 前向计算公式？\n      - [x] 1.4 RNN 存在什么问题？\n    - [x] 二、长短时记忆网络(Long Short Term Memory Network, LSTM) 篇\n      - [x] 2.1 为什么 需要 LSTM?\n      - [x] 2.2 LSTM 的结构是怎么样的?\n      - [x] 2.3 LSTM 如何缓解 RNN 梯度消失和梯度爆炸问题?\n      - [x] 2.3 LSTM 的流程是怎么样的?\n      - [x] 2.4 LSTM 中激活函数区别?\n      - [x] 2.5 LSTM的复杂度？\n      - [x] 2.6 LSTM 存在什么问题？\n    - [x] 三、GRU (Gated Recurrent Unit)\n      - [x] 3.1 为什么 需要 GRU?\n      - [x] 3.2 GRU 的结构是怎么样的?\n      - [x] 3.3 GRU 的前向计算?\n      - [x] 3.4 GRU 与其他 RNN系列模型的区别？\n    - [x] 四、RNN系列模型篇\n      - [x] 4.1 RNN系列模型 有什么特点？\n  - [x] **[Attention 常见面试篇](./3%20深度学习算法篇常见面试篇/Attention%20常见面试篇.md)**\n    - [x] 一、seq2seq 篇\n      - [x] 1.1 seq2seq （Encoder-Decoder）是什么？\n      - [x] 1.2 seq2seq 中 的 Encoder 怎么样？\n      - [x] 1.3 seq2seq 中 的 Decoder 怎么样？\n      - [x] 1.4 在 数学角度上 的 seq2seq ，你知道么？\n      - [x] 1.5 seq2seq 存在 什么 问题？\n    - [x] 二、Attention 篇\n      - [x] 2.1 什么是 Attention?\n      - [x] 2.2 为什么引入 Attention机制？\n      - [x] 2.3 Attention 有什么作用？\n      - [x] 2.4 Attention 流程是怎么样？\n      - [x] 2.5 Attention 的应用领域有哪些？\n    - [x] 三、Attention 变体篇\n      - [x] 3.1 Soft Attention 是什么？\n      - [x] 3.2 Hard Attention 是什么？\n      - [x] 3.3 Global Attention 是什么？\n      - [x] 3.4 Local Attention 是什么？\n      - [x] 3.5 self-attention 是什么？\n  - [x] **[生成对抗网络 GAN 常见面试篇](./3%20深度学习算法篇常见面试篇/生成对抗网络%20GAN%20常见面试篇.md)** \n    - [x] 一、动机\n    - [x] 二、介绍篇\n      - [x] 2.1 GAN 的基本思想\n      - [x] 2.2 GAN 基本介绍\n        - [x] 2.2.1 GAN 的基本结构\n        - [x] 2.2.2 GAN 的基本思想\n    - [x] 三、训练篇\n      - [x] 3.1 生成器介绍\n      - [x] 3.2 判别器介绍\n      - [x] 3.3 训练过程\n      - [x] 3.4 训练所涉及相关理论基础\n    - [x] 四、总结\n\n------\n## **Star-History**\n\n![star-history](https://api.star-history.com/svg?repos=jackaduma/awesome_NLP-Interview-Notes\u0026type=Date \"star-history\")\n\n------\n\n## Donation\nIf this project help you reduce time to develop, you can give me a cup of coffee :) \n\nAliPay(支付宝)\n\u003cdiv align=\"center\"\u003e\n\t\u003cimg src=\"./misc/ali_pay.png\" alt=\"ali_pay\" width=\"400\" /\u003e\n\u003c/div\u003e\n\nWechatPay(微信)\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"./misc/wechat_pay.png\" alt=\"wechat_pay\" width=\"400\" /\u003e\n\u003c/div\u003e\n\n------\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjackaduma%2Fawesome_nlp-interview-notes","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjackaduma%2Fawesome_nlp-interview-notes","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjackaduma%2Fawesome_nlp-interview-notes/lists"}