Master computer vision, deep learning, and embedded systems with hands-on projects.
Computer Vision
- OpenCV Library
- Image processing
Deep Learning
- History of deep learning
- Deep learning libraries and tools
- Basic concepts in deep learning
- Model architectures (CNNs, RNNs, transformers, ViTs, etc.)
- Data preparation
- Build and train model
- Evaluation metrics
- Multi-modal (text, image, video)
- Techniques to optimize model
- Distillation learning
- Model quantization
- Pruning and sparsity
- Hyperparameter tuning
- Weight sharing
- Deploy deep learning model
- Machine learning in production
- Transfer learning
- Self-supervised learning
- Generative models (e.g., GANs, VAEs)
- Attention mechanisms and transformers
- Explainability in deep learning
- Ethics and bias in deep learning
- Scaling deep learning
- Few-shot and zero-shot learning
- Deep learning in edge computing
- Federated learning
- Neural architecture search
- Deep learning: present and future
Embedded System
- Overview of embedded systems
- Embedded computing platforms for AI
- Sensors and cameras for vision tasks
- Accelerators for deep learning
- Real-time processing in embedded systems
- Power-efficient deep learning on edge devices
- Edge AI frameworks
- Model optimization for embedded systems
- Quantization
- Pruning
- Distillation
- Applications
- Object detection and tracking
- Face recognition
- Gesture recognition
- Autonomous navigation (e.g., drones, robots)
- Medical imaging on embedded devices
- Trends and challenges in embedded AI
Projects
- Image classification
- Object detection
- Object tracking
- Image segmentation
- Depth estimation
- Lane detection
- Drivable detection
- Self-driving car