HackMDAI / 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
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
Explainable Machine Learning/AI
[Explainable AI] 可解釋的機器學習與因果推斷
[Explainable AI] Transformer Interpretability Beyond Attention Visualization。Transformer可解釋性與視覺化
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
LLM(NLP) / Generative AI
有用的資源
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
- GenAI Interview Resources
- [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
- 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
- 包含相當全面而完整的提示工程教學文件，新手必讀Image Not Showing Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
- auto-prompter。還不錯用的自動提示詞優化工具、可以搭配gpt使用Image Not Showing Possible Reasons
- The image file may be corrupted
- The server hosting the image is unavailable
- The image path is incorrect
- The image format is not supported
- learnprompting.org/Prompt Engineering Guide。初學者的課程設計導向
- promptperfect。提示詞工程開發工具API
- LangGPT —— 人人都可编写高质量 Prompt
筆記、講座、文章摘要
State of AI Report 2023筆記
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
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
- 本文主要參考2023.06。lilianweng.github.io。LLM Powered Autonomous Agents。"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
- 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
LLM Optimization and Customization Series
[LLM] 大型語言模型的客製方案(施工中)
Customized solutions for LLM
- 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)
Deeplearning.ai GenAI/LLM系列課程筆記
- Generative AI with Large Language Models。 使用大型語言模型的生成式人工智能
Image Not Showing Possible Reasons- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Image Not Showing Possible Reasons- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
short cources
GenAI
- Large Language Models with Semantic Search。大型語言模型與語意搜索
- LangChain for LLM Application Development。使用LangChain進行LLM應用開發
- Finetuning Large Language Models。微調大型語言模型
- Prompt Engineering for Vision Models。視覺模型的提示工程
- 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
RAG
- [GenAI][RAG]Building and Evaluating Advanced RAG。建立與評估進階RAG
- [GenAI][RAG] Multi-Modal Retrieval-Augmented Generation and Evaluaion。多模態的RAG與評估
- [GenAI][RAG] Chunking Strategies & LLM Agentic Chunking
- [GenAI][RAG] Multi-Modal RAG Notes 多模態RAG檢索筆記
- [GenAI][RAG] Building Multimodal Search and RAG。多模態搜尋與RAG
AI Agents
Mulimodal
[Mulimodal] CVPR 2023。Multimodal Foundation Models : From Specialists to General-Purpose Assistants
多模態基礎模型研究回顧
(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
[Multimodal] 通用多模態模型資訊檢索器模型 UniIR: Training and Benchmarking Universal Multimodal Information Retrievers
[Multimodal] 多模態語言模型在自駕領域筆記 Multimodal Large Language Models for Autonomous Driving
Computer Vision
Object Detection
[Object Detection_YOLO] YOLOv7 論文筆記
ViT與Transformer相關
[Transformer_CV] Vision Transformer(ViT)重點筆記
[Transformer] Self-Attention與Transformer
[Transformer_CV] Masked Autoencoders(MAE)論文筆記
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
Autoencoder相關
[Autoencoder] Variational Sparse Coding (VSC)論文筆記
[Transformer_CV] Masked Autoencoders(MAE)論文筆記
Time Series
Deep Learning with Time Series data
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
Reinforcement learning
[RL] Fine-Tuning Language Models from Human Preferences (RLHF)論文筆記-ChatGPT鍊成術
[RL] Proximal Policy Optimization(PPO)
[RL] Q learning 與 Deep Q Network(DQN)
Edge AI / Deployment
模型部署與加速
[Deployment] AI模型部屬入門相關筆記
[Object Detection_YOLO] YOLOv7 論文筆記
Deploy YOLOv7 on Nvidia Jetson
Convert PyTorch model to TensorRT for 3-8x speedup
將PyTorch模型轉換為TensorRT，實現3-8倍加速
Accelerate multi-streaming cameras with DeepStream and deploy custom (YOLO) models
使用DeepStream加速多串流攝影機並部署客製(YOLO)模型
Use Deepstream python API to extract the model output tensor and customize model post-processing (e.g., YOLO-Pose)
使用Deepstream python API提取模型輸出張量並定製模型后處理（如：YOLO-Pose）
Model Quantization Note 模型量化筆記
NVIDIA Jetson 平台部署相關筆記
