Deep Learning: From Basics to Research

This course is a complete journey into deep learning — starting from absolute basics and progressing toward advanced research skills. It is designed for students, engineers, and enthusiasts who want to not just use deep learning models but deeply understand and create them. We begin with foundational concepts: neurons, activation functions, forward and backward propagation, optimization techniques, and classical architectures like MLPs (Multi-Layer Perceptron). Alongside theory, you will build projects from scratch using Python and frameworks like NumPy, gaining a strong intuition without relying on pre-built libraries. The second phase of the course shifts focus to research-level study. You'll learn how to read and interpret deep learning research papers, reproduce experiments, and critically analyze innovations. We explore how to identify gaps in current literature, design original experiments, and develop your own research projects. Key Highlights: 1. Build deep learning models from scratch 2. Study architectures like CNNs, RNNs, ANNs 3. In-depth math and theory explained in simple terms 4. Learn how to reproduce and critique research papers 5. Guidance on developing and writing your own research ideas 6. Hands-on projects and a final capstone research project 7. Community and mentorship for peer review and feedback Who is this course for? 1. Beginners with strong motivation 2. Intermediate learners wanting deeper, research-driven understanding 3. Future researchers, engineers, and innovators in AI Prerequisites: 1. Basic Python programming 2. Basic linear algebra and calculus (recommended, but not mandatory — we'll review)