AI Model Design, Development & Robotics 

This course covers how AI systems are designed, trained, fine-tuned, deployed, and integrated into intelligent machines. Participants progress from machine learning and deep learning fundamentals through fine-tuning, MLOps deployment, and AI robotics, including computer vision and reinforcement learning. 

Course Content

​

Week 1: Machine Learning Fundamentals 

• Supervised vs. unsupervised learning 

• Model evaluation basics 

Week 2: Deep Learning Foundations 

• Neural network basics 

• Backpropagation 

Week 3: Neural Network Architectures 

• Convolutional Neural Networks (CNNs) 

• Recurrent Neural Networks (RNNs) 

Week 4: Transformers 

• Attention mechanisms 

• Transformer architecture 

Week 5: Diffusion Models 

• Generative image model overview 

• Diffusion model use cases 

Week 6: Data Engineering for ML 

• Data pipelines 

• Feature engineering 

Week 7: Model Training 

• Training loops 

• Hyperparameter tuning 

Week 8: Fine-Tuning 

• Transfer learning 

• Fine-tuning workflows 

Week 9: LoRA & PEFT 

• Parameter-efficient fine-tuning techniques 

Week 10: Model Evaluation 

• Evaluation metrics 

• Bias detection 

• Validation strategies 

Week 11: MLOps & Deployment I 

• Docker fundamentals 

• Model serving