sut-ai/supplementary: Sharif University of Technology AI & Machine Learning Educational Resource Library

The AI team at Sharif University of Technology (SUT) has open-sourced the complete AI/ML educational resource library sut-ai/supplementary on GitHub, covering systematic learning materials from basic concepts to deep learning, suitable for university teaching and self-study advancement. This project is positioned as supplementary teaching material, which can be used both as an aid for formal courses and as a main learning path for self-learners.

In current AI education, high-quality systematic resources are scattered and lack a unified knowledge system. As a top technical university in Iran, the SUT AI team integrated open-source resources to launch the sut-ai/supplementary project. It is not a pile of materials but a carefully organized multi-level AI/ML educational resource library, with its core positioning being to provide supplementary materials that adapt to the needs of formal course assistance and self-study.

The resource library covers four major areas: 1. Basic AI concepts (definitions, history, differences between classical and modern AI, etc.); 2. Core machine learning theories (three major paradigms and mathematical foundations); 3. Deep learning technology stack (from basic neural networks to modern models like Transformer); 4. Practical applications and case studies (algorithm implementation in real scenarios).

The project has three key features: 1. Open-source sharing: Breaking geographical barriers, learners worldwide benefit from the accumulation of top universities; 2. Systematic: Providing a complete learning path to avoid knowledge gaps; 3. Multilingual adaptation potential: Structured organization facilitates translation and localization, with high credibility for Chinese learners.

The main audience includes university students (supplementing course understanding), self-learners (systematic learning guidance), teachers (enriching course content), and industry practitioners (solidifying theoretical foundations). Learning recommendations: Beginners should start with basic concepts and mathematics; experienced learners can directly choose specialized topics for study.

The project is based on GitHub and has three major advantages: 1. Convenient community contribution (submitting content via PR); 2. Traceable versions (clear update history); 3. Easy to fork and localize (other institutions can add local content).

This project is a model of open-source educational resources from universities, helping to narrow the educational gap and popularize AI technology. It is recommended that the Chinese community participate in translation and localization to benefit more users. In the future, we look forward to incorporating cutting-edge topics such as large language models, multimodal learning, and AI security to continuously enrich the AI education ecosystem.