Repository structure
• online/ – curated markdown files that contain links to external resources (arXiv, journals, blog posts).
• Root level .md files – organized by AI/ML domains
• computer-vision/ – detailed CV papers organized by specific topics
• offline/ – books & papers stored directly in the repo (PDF).
• offline/Books/ – textbooks, reference books
• offline/Papers/ – academic papers, slide decks, notes
• diagrams/ – visual resources and timeline diagrams
• scripts/ – utility scripts for repository maintenanceWhen you contribute, please read
CONTRIBUTING.mdfor rules on adding new PDFs or links.
This repository contains books and documents related to Machine Learning and Deep Learning. The goal is to create a clear and useful learning resource for study and reference to solve specific problems. These are documents I have collected throughout my studies. I hope everyone will find it helpful!
If you find it useful, please give me a star ⭐. It will be the motivation for me to continue developing this repo.
If you don't know where to start learning, check out: AI Roadmap. This roadmap will help you learn all about ML and DL, then you can dive deeper into a specific area.
- 📚 Offline Resources (PDF Files)
- 🌐 Online Resources (Curated Links)
- 📊 Diagrams & Visualizations
- 🛠️ Utilities
- Deep Learning with PyTorch
- Deep Learning Basic (VN language)
- Neural Networks from Scratch in Python
- Understanding Deep Learning
- Natural Language Processing with Python
- Practical Computer Vision
- Deep Learning from Scratch
- Deep Learning in Object Detection and Recognition
- Machine Learning Concepts
- AI and Machine Learning for Coders
- Hands-On Machine Learning with C++
- Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
- Introduction to Probability for Data Science
- MLOps - Machine Learning Engineering in Action
- Linear Algebra (University of Vermont)
- Linear Algebra from UC Davis
- A First Course in Linear Algebra
- Mathematics for Machine Learning
- Math for Deep Learning
- Classification Models: ResNet, DenseNet, EfficientNet, MobileNet, SE-Net, ShuffleNet, SqueezeNet, InceptionNet
- CNN Architectures: Lightweight FCN, Conditional Convolution, CNN fundamentals
- Vision Transformers: ViT, Recent advances, CNN-Transformer hybrid models
- OCR: Text Recognition, TrOCR Transformer-based OCR
- Image Classification: ConvNeXt, FractalNet, Inception-ResNet, NASNet, Xception
- Action Recognition: SlowFast Networks, Video Vision Transformer
- Image Captioning: Show, Attend and Tell
- Object Detection: YOLO series
- Specialized Topics: Mamba, MixUp Augmentation, High-Resolution Representation Learning
- Classic GANs: DCGAN, WGAN, Progressive GAN
- Conditional GANs: Conditional GAN, AC-GAN, InfoGAN
- Image-to-Image: CycleGAN, StackGAN (v1 & v2)
- Super Resolution: SRGAN
- RNNs: Basic RNN concepts, implementations
- LSTM: Convolutional LSTM, Backpropagation in LSTM
- GRU: Gated Recurrent Units fundamentals
- Transformers: Attention mechanisms, Deep Transformer models
- Modern Architectures: Mamba - Linear Time Sequence Modeling
- Word Embeddings: Word embedding techniques
- Normalization: Batch Normalization, Layer Normalization
- Regularization: Dropout techniques
- Optimization: Adam optimizer, learning rate strategies
- Training Techniques: Transfer Learning, Graph mode execution
- Neural Network Concepts: Synthetic Gradients, Decoupled Neural Interfaces
- Classification Metrics: Model evaluation techniques
- ROC Analysis: ROC curves and cutoff analysis
- Visualization: Multiple evaluation metrics visualization
- Descriptions: GNN, Multimodal LLMs, Diffusion Colorization, VAE
- Slides: Multimodal LLM, Math Solver with LLMs
- Tutorials: LangChain, Multi-task Learning
📋 Quick Access: computer-vision.md - Comprehensive curated list of CV papers with direct links
📁 Detailed Topics: computer-vision/ folder contains specialized guides:
- Landmark Papers - Historic milestones & must-read classics
- Image Classification - Classification models + Vision Transformers
- Object Detection - Detection & instance segmentation
- Semantic Segmentation - Segmentation techniques
- Video Understanding - Action recognition & video models
- Self-Supervised Learning - Representation learning without labels
📋 Coming Soon: natural-language-processing.md
This section is under development. Check back soon for curated NLP resources!
📋 Coming Soon: generative-models.md
This section is under development. Check back soon for generative AI resources!
📋 Coming Soon: reinforcement-learning.md
This section is under development. Check back soon for RL resources!
📋 Coming Soon: optimization.md
This section is under development. Check back soon for optimization techniques!
- For Beginners: Start with the AI Roadmap to understand learning paths
- For Specific Topics: Browse the online curated lists for latest papers and resources
- For Deep Study: Download PDFs from the offline collection for comprehensive learning
- For Visual Learners: Check out the diagrams and timeline visualizations
⭐ If you find this repository helpful, please give it a star to support continued development!