📚 Study Notes
This page gathers my self-study notes on large models, agents, and related AI systems topics. The homepage keeps a compact showcase, while this page is meant to expand as I continue reading and learning.
PyTorch Deep Learning Quickstart Notes
Topic: PyTorch, Deep Learning Fundamentals, CNNs, Model Training
A self-study note repository based on Xiaotudui’s PyTorch introductory course, organized as a notebook-based learning path from environment setup and data processing to convolutional networks, loss functions, optimizers, and complete training workflows. The repository reflects my hands-on practice in building a practical foundation for deep learning with PyTorch.
Link: GitHub Repository
D2L v2 Notes
Topic: Deep Learning, Computer Vision, Sequence Models, Transformer, BERT
A systematic self-study note repository based on Dive into Deep Learning v2, covering a broad range of topics from basic neural networks and convolutional models to object detection, sequence modeling, attention mechanisms, Transformer, and BERT. The repository is organized as a chapter-by-chapter notebook collection and reflects my effort to build a more complete understanding of modern deep learning methods.
Link: GitHub Repository
Andrew Ng Deep Learning Specialization Notes
Topic: Neural Networks, CNNs, Sequence Models, Optimization, Deep Learning Strategy
A self-study note repository based on Andrew Ng’s Deep Learning Specialization, covering core topics such as neural network foundations, training improvement techniques, machine learning strategy, convolutional networks, and sequence models. The repository combines lecture notes, quiz records, and programming assignments, reflecting my effort to systematically revisit the classical deep learning curriculum.
Link: GitHub Repository
LLM Learning Plan
Topic: Large Language Models, Model Architecture, Training, Alignment, Inference Optimization, Agents
A comprehensive self-study note repository for building a full-stack understanding of large language models, from mathematical foundations and core architectures to fine-tuning, RLHF, optimization, RAG, agents, and deployment. The project combines theory-oriented reading with hands-on notebook implementations.
Link: GitHub Repository
Document AI From OCR to Agentic Doc Extraction
Topic: OCR, Document AI, Agentic Document Extraction, RAG, AWS Pipelines
A self-study note repository based on the DeepLearning.AI course on document intelligence, covering the path from OCR and document parsing to agentic document understanding, RAG over structured documents, and cloud-based automation pipelines. The project combines notebook-based experiments with practical pipeline design.
Link: GitHub Repository
5-Day AI Agents Intensive Course with Google
Topic: AI Agents, Agent Architectures, Tool Use, Memory, Evaluation, Deployment
A self-study note repository based on Kaggle’s 5-Day AI Agents Intensive Course with Google, organized as a day-by-day learning path from prompt-driven agents to multi-agent communication and deployment. The repository focuses on course reproduction and structured note-taking through notebooks.
Link: GitHub Repository
