A comprehensive collection of AI/ML resources, tools, frameworks, and learning materials curated by Umit Kacar, PhD.
Last Updated: 2025-06-23 | Total Resources: 450+ | Categories: 15
Vision: To be the go-to resource hub for AI/ML practitioners, researchers, and developers worldwide - from beginners starting their journey to experts pushing the boundaries of artificial intelligence.
Mission:
- ๐ Accessibility: Organize and categorize AI/ML resources for easy discovery
- ๐ Currency: Maintain up-to-date, living documentation that evolves with the field
- ๐ Comprehensiveness: Cover the full spectrum from foundational concepts to cutting-edge research
- ๐ค Community: Foster an open-source community where everyone can contribute and benefit
- Curated Quality: Every resource is carefully selected for its value and relevance
- Practical Focus: Emphasis on tools and frameworks you can use today
- Broad Coverage: From LLMs to Quantum ML, Mobile AI to MLOps
- Active Maintenance: Regularly updated with new resources and fixed links
- Community Driven: Open to contributions from the global AI community
- ๐ Interactive Notebooks
- ๐ค Large Language Models (LLMs)
- ๐จ Generative AI & Stable Diffusion
- ๐๏ธ Computer Vision
- ๐ต Audio & Speech Processing
- ๐ Biometrics & Security
- ๐ฑ Mobile & Edge AI
- ๐ MLOps & Production
- ๐ฎ Reinforcement Learning
- โ๏ธ Quantum Machine Learning
- ๐ค AutoML & Neural Architecture Search
- ๐ Time Series Analysis
- ๐ธ๏ธ Graph Neural Networks
- ๐ง Tools & Frameworks
- ๐ Learning Resources
- ๐ผ Interview & Career
- Notebook Collection - Run AI/ML code directly in your browser
- Beginner Tutorials - Start your AI journey
- Advanced Examples - State-of-the-art implementations
- Awesome-LLM-Resources - Comprehensive LLM resource collection
- LLMs-Finetuning - Fine-tuning techniques and best practices
- LLMs-tricks - Tips, tricks, and optimization techniques
- IQA-with-LLMs - Image Quality Assessment using LLMs
- awesome-GANs-Stable-Diffusion - GANs and Stable Diffusion resources
- Awesome-ComfyUI-Beyond - ComfyUI workflows and extensions
- food-generative-ai - Food generation with AI
- image-enhancement - Image enhancement techniques
- Dark-Mode - Dark mode implementations
- SAM-Foundation-Models - Segment Anything Model resources
- Interactive-Image-Segmentation - Interactive segmentation tools
- tattoo_segmentation - Tattoo segmentation techniques
- Transformers-CNN-Segmentation - Transformer-based segmentation
- awesome-video-segmentation - Video segmentation resources
- awesome-video-inpainting - Video inpainting techniques
- pseudonymous-video-platform - Privacy-preserving video processing
- awesome-3D-Computer-Vision - 3D computer vision resources
- Speech Recognition - ASR models and tools
- Biometrics Overview - Comprehensive comparison of all biometric modalities
- Face Recognition - Deep learning approaches, anti-spoofing, and production systems
- Fingerprint Recognition - Minutiae extraction, deep learning, and sensor technologies
- Iris Recognition - IrisCode, deep learning methods, and liveness detection
- Voice Recognition - Speaker recognition, x-vectors, and ECAPA-TDNN
- Ear Recognition - Ear biometrics and segmentation
- Signature Verification - Offline/online signature verification
- Gait Recognition - Walking pattern analysis for identification
- Vein Recognition - NIR imaging for finger/palm vein patterns
- Multimodal Biometrics - Fusion strategies for multiple biometric traits
- DeepFake Detection - Detecting synthetic media
- mobile-apps-ai-ios-android - Mobile AI app development
- ai-edge-computing-tiny-embedded - Edge computing resources
- ai-flutter - Flutter + AI integration
- awesome-ncnn-collection - NCNN framework resources
- NCNN Mobile AI - NCNN framework comprehensive guide
- Onnxruntime-TensorRT - ONNX Runtime and TensorRT optimization
- Production Deployment - MLOps platforms and best practices
- RL Basics - Introduction to RL concepts
- Quantum ML Basics - Introduction to QML
- Quantum Algorithms - QAOA, VQE, quantum kernels
- QML Frameworks - PennyLane, Qiskit, TensorFlow Quantum
- AutoML Frameworks - AutoGluon, H2O, PyCaret, and more
- Neural Architecture Search - DARTS, ENAS, NAS algorithms
- Hyperparameter Optimization - Optuna, Ray Tune, Hyperopt
- Time Series Basics - Classical and modern forecasting methods
- Deep Learning for Time Series - LSTM, Transformer models
- Prophet & AutoTS - Automated forecasting tools
- GNN Fundamentals - GCN, GraphSAGE, GAT architectures
- PyTorch Geometric Guide - Implementation tutorials
- Graph Applications - Social networks, molecules, knowledge graphs
- Git-codes - Git commands and workflows
- Framework-Trending - Trending frameworks and libraries
- MLOps - MLOps best practices
- ai-python-backend - Python backend for AI services
- Web_Application - Web application development
- ai-js - AI with JavaScript
- ai-cplusplus - AI with C++
- ai-preprocessing - Data preprocessing techniques
- ai-ebook - AI/ML ebooks and papers
- Software-Development-Lessons - Software development best practices
- Turkish AI Resources - ๐น๐ท Tรผrkรงe yapay zeka kaynaklarฤฑ
- NLP_Research - NLP research papers and tutorials
- FAANG Interview Prep - Complete FAANG AI/ML interview guide
- AI Marketing Apps - AI in marketing applications
Feel free to contribute to this collection! Please read our contribution guidelines before submitting PRs.
This repository is licensed under the MIT License - see the LICENSE file for details.
Maintained with โค๏ธ by Umit Kacar