# AI / ML領域相關學習筆記入口頁面 --- # Machine Learning ## Basic ##### [[ML] 機器學習基礎指標：Maximum Likelihood Estimation、Softmax、Entropy、 KL Divergence](https://hackmd.io/@YungHuiHsu/SyIdBun4a) ## Dimensionality Reduction ##### [[ML] Dimensionality Reduction 降維演算法 - Deep Targeted Discriminant Analysis (DeepTDA) ，t-SNE 與 UMAP之外的新選擇](https://hackmd.io/@YungHuiHsu/rk-G8BpBT) ## Explainable Machine Learning/AI ##### [[Explainable AI] 可解釋的機器學習與因果推斷](https://hackmd.io/o1-JBK9ITb27phle-ygd4w) ##### [[Explainable AI] Transformer Interpretability Beyond Attention Visualization。Transformer可解釋性與視覺化](https://hackmd.io/SdKCrj2RTySHxLevJkIrZQ) # Deep Learning ## 入門 ##### [Deep Learning：用Python進行深度學習的基礎理論實作 - 讀書筆記](https://yunghui.notion.site/Deep-Learning-Python-bbf63fe9adca46afb39f99ab11667200) --- # LLM(NLP) / Generative AI ### 有用的資源 #### [awesome-generative-ai-guide](https://github.com/aishwaryanr/awesome-generative-ai-guide) - AWS的 Gen AI Tech Lead，內有豐富學習資源，包括： * [Monthly Best GenAI Papers List](https://github.com/aishwaryanr/awesome-generative-ai-guide?tab=readme-ov-file#star-best-genai-papers-list-january-2024) * [GenAI Interview Resources](https://github.com/aishwaryanr/awesome-generative-ai-guide?tab=readme-ov-file#computer-interview-prep) * [Applied LLMs Mastery 2024 (created by Aishwarya Naresh Reganti) course material](Applied LLMs Mastery 2024 (created by Aishwarya Naresh Reganti) course material) * [List of all GenAI-related free courses (over 85 listed)](List of all GenAI-related free courses (over 85 listed)) * [List of code repositories/notebooks for developing generative AI applications](List of code repositories/notebooks for developing generative AI applications) ##### [OpenAI Cookbook](https://github.com/openai/openai-cookbook) - OpenAI 官方範例，有許多有效利用的範例 - 不管是Langchain vs LlamaIndex，預設底層還是call OPENAI的API，最輕量有效、且文件細節最詳細的還是要看OPANAI提供的範例 #### Prompt Engineering - [Prompt Engineering Guide](https://www.promptingguide.ai/) - :pencil2:包含相當全面而完整的提示工程教學文件，新手必讀 - [auto-prompter](https://openai-prompting-helper-e924c62387f55170bc7836f9f-ffoprvkqsa-uc.a.run.app/auto-prompter/playground/)。:100:還不錯用的自動提示詞優化工具、可以搭配gpt使用 - [learnprompting.org/Prompt Engineering Guide](https://learnprompting.org/)。初學者的課程設計導向 - [promptperfect](https://promptperfect.jina.ai/)。提示詞工程開發工具API - [LangGPT —— 人人都可编写高质量 Prompt ](https://github.com/langgptai/LangGPT/blob/main/README_zh.md) ### 筆記、講座、文章摘要 ##### [State of AI Report 2023筆記](https://hackmd.io/@YungHuiHsu/rJ6_pnHXa) 掌握近期AI趨勢的快速摘要，內容深淺適中 ##### [2022。AACL-IJCNLP。Recent Advances in Pre-trained Language Models:Why Do They Work and How to Use Them](https://hackmd.io/@YungHuiHsu/B1uq8q_Gp) 李弘毅老師實驗室出品，非常棒的語言模型近期(2022年)進展的介紹 主要整理PEFT: Parameter-Efficient Finetuning部分說明 - 投影片大綱: - Part 4 How to use PLMs: Parameter-efficient fine-tuning ##### [How Agents for LLM Perform Task Planning。大型語言模型的代理如何進行任務規劃](https://hackmd.io/@YungHuiHsu/rkK52BkQp) + 本文主要參考[2023.06。lilianweng.github.io。LLM Powered Autonomous Agents](https://lilianweng.github.io/posts/2023-06-23-agent/)。"Planning"章節進行翻譯與補充 - 這篇文章很好的回顧了當前(2023.06為止)LLM Agents(任務代理)重要的核心思想 ##### [2023.09。Dr. Ed H. Chi。The Large Language Model Revolution](https://hackmd.io/@YungHuiHsu/HyTZ6idG6) - 模型的推理能力 Reasoning * 連鎖思考提示 (Chain-of-thought prompting)：<問題 => 解釋 => 答案> * 自我一致性 (Self-consistency)：生成相同問題的多個答案，然後選擇最常見的 * 由小至大的提示 (Least-to-most prompting)：將問題分解並解決子問題 - 指令微調 (Instruction finetuning)：教導大型語言模型 (LLMs) 遵循指令 ### 大型語言模型優化與客製系列<br> LLM Optimization and Customization Series ##### [[LLM] 大型語言模型的客製方案(施工中)<br>Customized solutions for LLM]([施工中](https://hackmd.io/@YungHuiHsu/H1DP86sba)) - Prompt engineering - Prompt learning - Parameter-efficient fine-tuning (PEFT) - Fine-tuning ##### [[LLM] 索增強生成（Retrieval Augmented Generation，RAG)。讓模型開啟知識包外掛(施工中)](https://hackmd.io/@YungHuiHsu/SJ5BsLoWp) ### [Deeplearning.ai GenAI/LLM系列課程筆記](https://learn.deeplearning.ai/) - [Generative AI with Large Language Models](https://hackmd.io/1N5imGRgTnC5JofoXu0j2A)。 使用大型語言模型的生成式人工智能 ![image](https://hackmd.io/_uploads/BkXI2znTp.png =30x) ![image](https://hackmd.io/_uploads/S1uv3Ghpa.png =150x) #### short cources ##### GenAI - [Large Language Models with Semantic Search。大型語言模型與語意搜索 ](https://hackmd.io/@YungHuiHsu/rku-vjhZT) - [LangChain for LLM Application Development。使用LangChain進行LLM應用開發](https://hackmd.io/1r4pzdfFRwOIRrhtF9iFKQ) - [Finetuning Large Language Models。微調大型語言模型](https://hackmd.io/@YungHuiHsu/HJ6AT8XG6) - [Prompt Engineering for Vision Models。視覺模型的提示工程](https://hackmd.io/@YungHuiHsu/rkqs588d0) - [Preprocessing Unstructured Data for LLM Applications。大型語言模型(LLM)應用的非結構化資料前處理](https://hackmd.io/@YungHuiHsu/BJDAbgpgR) ##### RAG - [[GenAI][RAG]Building and Evaluating Advanced RAG。建立與評估進階RAG](https://hackmd.io/@YungHuiHsu/rkqGpCDca) - [[GenAI][RAG] Multi-Modal Retrieval-Augmented Generation and Evaluaion。多模態的RAG與評估 ](https://hackmd.io/@YungHuiHsu/B1LJcOlfA) - [[GenAI][RAG] Chunking Strategies & LLM Agentic Chunking](https://hackmd.io/@YungHuiHsu/Hk1O6n7x0) - [[GenAI][RAG] Multi-Modal RAG Notes 多模態RAG檢索筆記](https://hackmd.io/@YungHuiHsu/B1LJcOlfA) - [[GenAI][RAG] Building Multimodal Search and RAG。多模態搜尋與RAG ](https://hackmd.io/@YungHuiHsu/Bk3Dh-UdR) ##### AI Agents - [AI Agents in LangGraph](https://hackmd.io/@YungHuiHsu/BJTKpkEHC) - [Long-Term Agentic Memory With LangGraph](https://hackmd.io/@YungHuiHsu/S1f1cyOnke) --- # Mulimodal ##### [[Mulimodal] CVPR 2023。Multimodal Foundation Models : From Specialists to General-Purpose Assistants<br>多模態基礎模型研究回顧](https://hackmd.io/@YungHuiHsu/HkOjXPg46) ##### (施工中)[[Multimodal]多模態學習(MultiModal Learning)與CLIP]() ##### [[Multimodal] LLaVA鍊成術-視覺指令調節 Visual Instruction Tuning](https://hackmd.io/@YungHuiHsu/HyMgBbjSa) ##### [[Multimodal] 通用多模態模型資訊檢索器模型 UniIR: Training and Benchmarking Universal Multimodal Information Retrievers](https://hackmd.io/@YungHuiHsu/rJVsI68B6) ##### [[Multimodal] 多模態語言模型在自駕領域筆記 Multimodal Large Language Models for Autonomous Driving](https://hackmd.io/@YungHuiHsu/HJzyHId4T) - [2311。A Survey on Multimodal Large Language Models for Autonomous Driving](https://arxiv.org/abs/2311.12320) --- # Computer Vision ### Object Detection ##### [[Object Detection_YOLO] YOLOv7 論文筆記](https://hackmd.io/xhLeIsoSToW0jL61QRWDcQ) ### ViT與Transformer相關 ##### [[Transformer_CV] Vision Transformer(ViT)重點筆記](https://hackmd.io/tMw0oZM6T860zHJ2jkmLAA) ##### [[Transformer] Self-Attention與Transformer](https://hackmd.io/fmJx3K4ySAO-zA0GEr0Clw) ##### [[Transformer_CV] Masked Autoencoders(MAE)論文筆記](https://hackmd.io/lTqNcOmQQLiwzkAwVySh8Q) ## Deep Learning相關筆記 ### Self-supervised Learning ##### [[Self-supervised] Self-supervised Learning 與 Vision Transformer重點筆記與近期(2021)發展](https://hackmd.io/7t35ALztT56STzItxo3UiA) ### Autoencoder相關 ##### [[Autoencoder] Variational Sparse Coding (VSC)論文筆記](https://hackmd.io/MXxa8zesRhym4ahu7OJEfQ) ##### [[Transformer_CV] Masked Autoencoders(MAE)論文筆記](https://hackmd.io/lTqNcOmQQLiwzkAwVySh8Q) --- # Time Series ##### [Deep Learning with Time Series data](https://hackmd.io/@YungHuiHsu/r1yCihCPo) 彙整2022年底深度學習方法在處理時間序列資料上的資源、趨勢與SOTA模型， ##### [TS2Vec(Towards Universal Representation of Time Series) 論文筆記](https://hackmd.io/@YungHuiHsu/SJbzRpIYs) --- # Reinforcement learning ##### [[RL] Fine-Tuning Language Models from Human Preferences (RLHF)論文筆記-ChatGPT鍊成術](https://hackmd.io/@YungHuiHsu/Sy5Ug7iV6) ![image](https://hackmd.io/_uploads/S1q5WVsET.png =300x) ##### [[RL] Proximal Policy Optimization(PPO)](https://hackmd.io/@YungHuiHsu/SkUb3aBX6) ##### [[RL] Q learning 與 Deep Q Network(DQN)](https://hackmd.io/@YungHuiHsu/BJgnMHbUH6) --- --- # Edge AI / Deployment ### 模型部署與加速 ##### [[Deployment] AI模型部屬入門相關筆記](https://hackmd.io/G80HMJRmSwaaLD8W1PHUPg) ##### [[Object Detection_YOLO] YOLOv7 論文筆記](https://hackmd.io/xhLeIsoSToW0jL61QRWDcQ) ##### [Deploy YOLOv7 on Nvidia Jetson](https://hackmd.io/kZftj6AgQmWJsbXsswIwEQ) ##### [Convert PyTorch model to TensorRT for 3-8x speedup<br>將PyTorch模型轉換為TensorRT，實現3-8倍加速](https://hackmd.io/_oaJhYNqTvyL_h01X1Fdmw?both) ##### [Accelerate multi-streaming cameras with DeepStream and deploy custom (YOLO) models<br>使用DeepStream加速多串流攝影機並部署客製(YOLO)模型](https://hackmd.io/@YungHuiHsu/rJKx-tv4h) ##### [Use Deepstream python API to extract the model output tensor and customize model post-processing (e.g., YOLO-Pose)<br>使用Deepstream python API提取模型輸出張量並定製模型后處理（如：YOLO-Pose）](https://hackmd.io/@YungHuiHsu/rk41ISKY2) ##### [Model Quantization Note 模型量化筆記](https://hackmd.io/riYLcrp1RuKHpVI22oEAXA) ### NVIDIA Jetson 平台部署相關筆記 ![](https://i.imgur.com/S5QFcnE.png =400x) ##### 基本環境設定 ##### [Jetson AGX Xavier 系統環境設定1_在windows10環境連接與安裝](https://hackmd.io/@YungHuiHsu/HJ2lcU4Rj) ##### [Jetson AGX Xavier 系統環境設定2_Docker安裝或從源程式碼編譯](https://hackmd.io/k-lnDTxVQDWo_V13WEnfOg) ##### [NVIDIA Container Toolkit 安裝筆記](https://hackmd.io/wADvyemZRDOeEduJXA9X7g) ##### [Jetson 邊緣裝置查詢系統性能指令jtop](https://hackmd.io/VXXV3T5GRIKi6ap8SkR-tg) ##### [Jetson Network Setup 網路設定](https://hackmd.io/WiqAB7pLSpm2863N2ISGXQ) ##### [OpenCV turns on cuda acceleration in Nvidia Jetson platform<br>OpenCV在Nvidia Jetson平台開啟cuda加速](https://hackmd.io/6IloyiWMQ_qbIpIE_c_1GA) ---