Spaces:
Running
Running
更新版面呈現
Browse files
README.md
CHANGED
|
@@ -7,178 +7,101 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
<
|
| 11 |
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
<p align="center">
|
| 15 |
-
<img src="./images/DeepLearning101.JPG" width="50%" />
|
| 16 |
-
|
| 17 |
-
<p align="center">
|
| 18 |
-
<a href="https://www.facebook.com/groups/525579498272187/">台灣人工智慧社團</a>
|
| 19 |
-
</p>
|
| 20 |
-
|
| 21 |
-
<p align="center">
|
| 22 |
-
<a href="http://DeepLearning101.TWMAN.ORG">http://DeepLearning101.TWMAN.ORG</a> |
|
| 23 |
-
<a href="https://huggingface.co/DeepLearning101">https://huggingface.co/DeepLearning101</a> |
|
| 24 |
-
<a href="https://www.youtube.com/@DeepLearning101">https://www.youtube.com/@DeepLearning101</a>
|
| 25 |
|
|
|
|
| 26 |
|
| 27 |
-
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
<details open>
|
| 32 |
-
<summary><strong>語音處理</strong></summary>
|
| 33 |
-
|
| 34 |
-
<details close>
|
| 35 |
-
<summary>Speech Recognition (語音識別)</summary>
|
| 36 |
-
|
| 37 |
-
- [中文語音識別](https://www.twman.org/AI/ASR)
|
| 38 |
-
- [語音識別質檢+時間戳:Whisper Large V2](https://huggingface.co/spaces/DeepLearning101/Speech-Quality-Inspection_whisperX)
|
| 39 |
-
- [Whisper](https://github.com/Deep-Learning-101/Speech-Processing-Paper/blob/main/Whisper.md)
|
| 40 |
-
- [WeNet](https://github.com/Deep-Learning-101/Speech-Processing-Paper/blob/main/WeNet.md)
|
| 41 |
-
- [FunASR](https://github.com/Deep-Learning-101/Speech-Processing-Paper/blob/main/FunASR.md)
|
| 42 |
-
|
| 43 |
-
</details>
|
| 44 |
|
| 45 |
-
|
| 46 |
-
<summary>Speaker Recognition (聲紋識別)</summary>
|
| 47 |
|
| 48 |
-
|
| 49 |
-
- [WeSpeaker](https://github.com/Deep-Learning-101/Speech-Processing-Paper/blob/main/WeSpeaker.md)
|
| 50 |
-
- [SincNet](https://github.com/Deep-Learning-101/Speech-Processing-Paper/blob/main/SincNet.md)
|
| 51 |
|
| 52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
-
|
| 55 |
-
<summary>Speech Enhancement (語音增強)</summary>
|
| 56 |
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
|
| 61 |
-
</details>
|
| 62 |
|
| 63 |
-
|
| 64 |
-
<summary>Speech Separation (語音分離)</summary>
|
| 65 |
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
-
|
| 72 |
|
| 73 |
-
|
| 74 |
-
|
| 75 |
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
- [VALL-E:微軟全新語音合成模型可以在3秒內復制任何人的聲音](https://zhuanlan.zhihu.com/p/598473227)
|
| 81 |
-
- [BLSTM-RNN、Deep Voice、Tacotron…你都掌握了吗?一文总结语音合成必备经典模型(一)](https://new.qq.com/rain/a/20221204A02GIT00)
|
| 82 |
-
- [Tacotron2、GST、Glow-TTS、Flow-TTS…你都掌握了吗?一文总结语音合成必备经典模型(二)](https://cloud.tencent.com/developer/article/2250062)
|
| 83 |
-
- Bark:https://github.com/suno-ai/bark
|
| 84 |
-
- [最強文本轉語音工具:Bark,本地安裝+雲端部署+在線體驗詳細教程](https://zhuanlan.zhihu.com/p/630900585)
|
| 85 |
-
- [使用Transformers 優化文本轉語音模型Bark](https://zhuanlan.zhihu.com/p/651951136)
|
| 86 |
|
| 87 |
-
</details>
|
| 88 |
</details>
|
| 89 |
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
#### [大型語言模型(Large Language Model,LLM),想要嗎?](https://blog.twman.org/2023/04/GPT.html)
|
| 93 |
-
#### [基於機器閱讀理解的指令微調的統一信息抽取框架之診斷書醫囑擷取分析](https://blog.twman.org/2023/07/HugIE.html):https://huggingface.co/spaces/DeepLearning101/IE101TW
|
| 94 |
-
|
| 95 |
-
<details open>
|
| 96 |
-
<summary><strong>自然語言處理</strong></summary>
|
| 97 |
-
|
| 98 |
-
<details open>
|
| 99 |
-
<summary>Large Language Model (大語言模型)</summary>
|
| 100 |
-
|
| 101 |
-
- [LangChain](https://github.com/Deep-Learning-101/Natural-Language-Processing-Paper#langchain)
|
| 102 |
-
- [Retrieval Augmented Generation](https://github.com/Deep-Learning-101/Natural-Language-Processing-Paper#rag)
|
| 103 |
-
- [LLM Model](https://github.com/Deep-Learning-101/Natural-Language-Processing-Paper#llm-%E6%A8%A1%E5%9E%8B%E4%BB%8B%E7%B4%B9)
|
| 104 |
-
|
| 105 |
-
</details>
|
| 106 |
-
|
| 107 |
-
<details close>
|
| 108 |
-
<summary>Information/Event Extraction (資訊/事件擷取)</summary>
|
| 109 |
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
|
|
|
|
|
|
| 113 |
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
<details close>
|
| 117 |
-
<summary>Machine Reading Comprehension (機器閱讀理解)</summary>
|
| 118 |
-
|
| 119 |
-
- [中文機器閱讀理解](https://www.twman.org/AI/NLP/MRC)
|
| 120 |
-
- [繁體中文閱讀理解:Bert](https://huggingface.co/spaces/DeepLearning101/Reading-Comprehension_Bert)
|
| 121 |
-
|
| 122 |
-
</details>
|
| 123 |
-
|
| 124 |
-
<details close>
|
| 125 |
-
<summary>Named Entity Recognition (命名實��識別)</summary>
|
| 126 |
-
</details>
|
| 127 |
-
|
| 128 |
-
<details close>
|
| 129 |
-
<summary>Correction (糾錯)</summary>
|
| 130 |
-
</details>
|
| 131 |
-
|
| 132 |
-
<details close>
|
| 133 |
-
<summary>Classification (分類)</summary>
|
| 134 |
-
</details>
|
| 135 |
-
|
| 136 |
-
<details close>
|
| 137 |
-
<summary>Similarity (相似度)</summary>
|
| 138 |
-
</details>
|
| 139 |
-
|
| 140 |
-
</details>
|
| 141 |
-
|
| 142 |
-
### [Computer vision (電腦視覺)](https://www.twman.org/AI/CV):[針對物件或場景影像進行分析與偵測](https://github.com/Deep-Learning-101/Computer-Vision-Paper)。
|
| 143 |
-
|
| 144 |
-
#### [用PaddleOCR的PPOCRLabel來微調醫療診斷書和收據](https://blog.twman.org/2023/07/wsl.html)
|
| 145 |
-
|
| 146 |
-
|
| 147 |
-
<details open>
|
| 148 |
-
<summary><strong>圖像處理:</strong></summary>
|
| 149 |
|
| 150 |
-
|
| 151 |
-
|
| 152 |
|
| 153 |
-
|
| 154 |
-
|
| 155 |
|
| 156 |
-
|
| 157 |
|
| 158 |
-
|
| 159 |
-
|
| 160 |
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
|
| 166 |
-
|
|
|
|
|
|
|
| 167 |
|
| 168 |
-
|
| 169 |
-
<summary>Document Understanding (文件理解)</summary>
|
| 170 |
-
</details>
|
| 171 |
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
</details>
|
| 175 |
|
| 176 |
-
|
| 177 |
-
|
| 178 |
-
|
|
|
|
|
|
|
| 179 |
|
| 180 |
-
|
| 181 |
-
<summary>Face Recognition (人臉識別)</summary>
|
| 182 |
-
</details>
|
| 183 |
|
| 184 |
-
</
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
<div align="center">
|
| 11 |
|
| 12 |
+
Deep Learning 101
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
+
**Deep Learning 101, Taiwan’s pioneering and highest deep learning meetup, launched on 2016/11/11 @ 83F, Taipei 101**
|
| 15 |
|
| 16 |
+
AI是一條孤獨且充滿惶恐及未知的旅程,花俏絢麗的收費課程或活動絕非通往成功的捷徑。<br>
|
| 17 |
+
衷心感謝當時來自不同單位的AI同好參與者實名分享的寶貴經驗;如欲移除資訊還請告知。<br>
|
| 18 |
+
由 [TonTon Huang Ph.D.](https://twman.org) 發起,及其當時任職公司(台灣雪豹科技)無償贊助場地及茶水點心。<br>
|
| 19 |
+
Deep Learning 101 創立初衷,是為了普及與分享深度學習及AI領域的尖端知識,深信AI的價值在於解決真實世界的商業問題。
|
| 20 |
|
| 21 |
+
<img src="./images/DeepLearning101.JPG" width="50%" />
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
+
---
|
|
|
|
| 24 |
|
| 25 |
+
🌟 快速連結 (Quick Links)
|
|
|
|
|
|
|
| 26 |
|
| 27 |
+
[](https://www.youtube.com/@DeepLearning101)
|
| 28 |
+
[](https://www.facebook.com/groups/525579498272187/)
|
| 29 |
+
[](https://deep-learning-101.github.io/)
|
| 30 |
+
[](https://github.com/Deep-Learning-101)
|
| 31 |
+
[](https://www.twman.org/DeepLearning101)
|
| 32 |
+
[](https://huggingface.co/DeepLearning101)
|
| 33 |
|
| 34 |
+
🚀 探索 AI 領域 (Tech Hub):
|
|
|
|
| 35 |
|
| 36 |
+
| [](https://deep-learning-101.github.io/Large-Language-Model) | [](https://deep-learning-101.github.io/Natural-Language-Processing) | [](https://deep-learning-101.github.io/Computer-Vision) | [](https://deep-learning-101.github.io/Speech-Processing) |
|
| 37 |
+
| :---: | :---: | :---: | :---: |
|
| 38 |
+
| [🔗 GitHub Papers](https://github.com/Deep-Learning-101/Natural-Language-Processing-Paper?tab=readme-ov-file#llm) | [🔗 GitHub Papers](https://github.com/Deep-Learning-101/Natural-Language-Processing-Paper) | [🔗 GitHub Papers](https://github.com/Deep-Learning-101/Computer-Vision-Paper) | [🔗 GitHub Papers](https://github.com/Deep-Learning-101/Speech-Processing-Paper) |
|
| 39 |
|
|
|
|
| 40 |
|
| 41 |
+
📚 精選資源導航
|
|
|
|
| 42 |
|
| 43 |
+
**🔥 嚴選 (必讀)**
|
| 44 |
+
* [<kbd>策略</kbd> AI新賽局:企業的入門策略指南](/Blog/AIBeginner)
|
| 45 |
+
* [<kbd>評測</kbd> 臺灣 LLM 性能評測與在地化分析](/Blog/TW-LLM-Benchmark)
|
| 46 |
+
* [<kbd>實戰</kbd> 從零到一:打造高精準度 RAG 系統](/RAG)
|
| 47 |
+
* [<kbd>避坑</kbd> 避開 AI Agent 開發陷阱與解決方案](/agent)
|
| 48 |
+
* [<kbd>手把手</kbd> Cloudflared 實作內網穿透 (Tunnel)](/Blog/Cloudflared-Tunnel)
|
| 49 |
+
* [<kbd>爆火</kbd> OpenClaw(MoltBot/Clawdbot)讓您焦慮嗎?](/Agent/OpenClaw-Moltbot-Clawdbot)
|
| 50 |
|
| 51 |
+
---
|
| 52 |
|
| 53 |
+
<details>
|
| 54 |
+
<summary><b>🛠️ 實戰工具 & Agent 框架</b></summary>
|
| 55 |
|
| 56 |
+
* [Dify, Coze, n8n, AutoGen 熱門框架比較](/Blog/Dify-Coze-n8n-AutoGen-LangChain)
|
| 57 |
+
* [推論加速:vLLM, Ollama, SGLang](/Blog/vLLM-Ollama-SGLang-LLaMAcpp)
|
| 58 |
+
* [Gemini + LangGraph 全端實戰](/gemini-fullstack-langgraph/FinGenAI)
|
| 59 |
+
* [基於 AutoGen 的 FinRobot 體驗](/FinRobot/FinRobot-GOOGL)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
|
|
|
|
| 61 |
</details>
|
| 62 |
|
| 63 |
+
<details>
|
| 64 |
+
<summary><b>📝 論文快遞</b></summary>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
|
| 66 |
+
* [Agentic AI:Gemini 3.1 WebMCP 實戰](/Agent/Gemini-3-1_WebMCP_Deep-Think)
|
| 67 |
+
* [NVIDIA PersonaPlex 全雙工語音 AI 深度技術分析](/LLM/PersonaPlex)
|
| 68 |
+
* [CoT (思维鏈) is not explainability](/Paper/Chain-of-Thought)
|
| 69 |
+
* [arXiv: Potemkin Understanding in LLMs](/Paper/2506.21521_Potemkin-Understanding)
|
| 70 |
+
* [arXiv: Agentic Reasoning](/Paper/2502.04644_Oxford_Agentic-Reasoning.html)
|
| 71 |
|
| 72 |
+
</details>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
+
<details>
|
| 75 |
+
<summary><b>📝 產業趨勢</b></summary>
|
| 76 |
|
| 77 |
+
* [💰 GenAI 在金融產業的應用分析](/Blog/AIFinTech)
|
| 78 |
+
* [🤖 2025 趨勢:AI Robot 陪伴型機器人](/Blog/robot)
|
| 79 |
|
| 80 |
+
</details>
|
| 81 |
|
| 82 |
+
<details>
|
| 83 |
+
<summary><b>🚧 踩坑指南 & 科普入門</b></summary>
|
| 84 |
|
| 85 |
+
* [🎓 白話文科普 GenAI (硬體/數據)](/GenAI)
|
| 86 |
+
* [🛑 LLM 打完收工?硬體升級重要性](/1010LLM)
|
| 87 |
+
* [📘 LLM 入門完整指南:原理與應用](/0204LLM)
|
| 88 |
+
* [🎨 Diffusion Model 圖像生成解析](/diffusion)
|
| 89 |
+
* [💻 訓練微調 VRAM 估算指南](/GPU)
|
| 90 |
+
* [🎙️ ASR/TTS 語音開發避坑](/asr-tts)
|
| 91 |
+
* [📝 NLP 自然語言開發避坑](/nlp)
|
| 92 |
+
* [🐧 Ubuntu 深度學習環境安裝教學](/101)
|
| 93 |
|
| 94 |
+
</details>
|
|
|
|
|
|
|
| 95 |
|
| 96 |
+
<details>
|
| 97 |
+
<summary><b>🛡️ AI 資安與 AIxCC 競賽</b></summary>
|
|
|
|
| 98 |
|
| 99 |
+
* [🏆 冠軍團隊:亞特蘭大 (Team-Atlanta) 解析](/cyber/AIxCC-Atlanta)
|
| 100 |
+
* [🥈 亞軍團隊:Trail of Bits 解析](/cyber/AIxCC-Buttercup)
|
| 101 |
+
* [🐚 Shellphish:用 LLMs 解決 CTF 挑戰](/cyber/AIxCC-shellphish)
|
| 102 |
+
* [🛡️ AI 大模型安全護欄綜合報告](/cyber/LLM-Guard)
|
| 103 |
+
* [⚔️ LLM 安全攻防策略深度解析](/cyber/LLM-Offense)
|
| 104 |
|
| 105 |
+
</details>
|
|
|
|
|
|
|
| 106 |
|
| 107 |
+
</div>
|