Master computer vision, deep learning, and embedded systems with hands-on projects.

Computer Vision

  1. OpenCV Library
  2. Image processing

Deep Learning

  1. History of deep learning
  2. Deep learning libraries and tools
  3. Basic concepts in deep learning
  4. Model architectures (CNNs, RNNs, transformers, ViTs, etc.)
  5. Data preparation
  6. Build and train model
  7. Evaluation metrics
  8. Multi-modal (text, image, video)
  9. Techniques to optimize model
    • Distillation learning
    • Model quantization
    • Pruning and sparsity
    • Hyperparameter tuning
    • Weight sharing
  10. Deploy deep learning model
  11. Machine learning in production
  12. Transfer learning
  13. Self-supervised learning
  14. Generative models (e.g., GANs, VAEs)
  15. Attention mechanisms and transformers
  16. Explainability in deep learning
  17. Ethics and bias in deep learning
  18. Scaling deep learning
  19. Few-shot and zero-shot learning
  20. Deep learning in edge computing
  21. Federated learning
  22. Neural architecture search
  23. Deep learning: present and future

Embedded System

  1. Overview of embedded systems
  2. Embedded computing platforms for AI
  3. Sensors and cameras for vision tasks
  4. Accelerators for deep learning
  5. Real-time processing in embedded systems
  6. Power-efficient deep learning on edge devices
  7. Edge AI frameworks
  8. Model optimization for embedded systems
    • Quantization
    • Pruning
    • Distillation
  9. Applications
    • Object detection and tracking
    • Face recognition
    • Gesture recognition
    • Autonomous navigation (e.g., drones, robots)
    • Medical imaging on embedded devices
  10. Trends and challenges in embedded AI

Projects

  1. Image classification
  2. Object detection
  3. Object tracking
  4. Image segmentation
  5. Depth estimation
  6. Lane detection
  7. Drivable detection
  8. Self-driving car