This course provides an in-depth introduction to Generative AI over 30 weeks. The first half covers AI fundamentals, machine learning concepts, and Python programming, progressing to deep learning, reinforcement learning, and Natural Language Processing (NLP). Students are introduced to various generative models, including probabilistic models and Variational Autoencoders (VAEs), and work on a generative AI project starting from Week 6.
The second half delves into advanced topics, such as cloud-based ML using AWS, Generative Adversarial Networks (GANs), advanced GAN architectures, and transformers. Transfer learning and ethical considerations in AI are also explored. The course concludes with a final project, allowing students to apply generative AI techniques in a practical setting.
Semester 1: Week 1 – 14
Week 1: Fundamentals of AI
• Introduction to AI
• Understanding the basics of Artificial Intelligence and historical context.
Week 2-3: Fundamentals of Machine Learning
• Review of machine learning concepts.
• Supervised vs Unsupervised learning.
• Basics of neural networks.
Week 4-5: Python and Mathematical Foundation
• Basics of Python
• Introduction to libraries like NumPy, Pandas, and Matplotlib
• Introduction to Linear Algebra, Calculus, and Statistics for ML
• Key concepts that underpin ML algorithms.
Week 6-8: Deep Learning Basics and Reinforcement Learning
• Introduction to deep learning.
• Neural network architectures.
• Activation functions and backpropagation.
• Introduction to reinforcement learning.
• Applying reinforcement learning to generative tasks.
Week 9-10: Introduction to Generative AI
• Introduction to Generative AI
• Understanding generative models.
• Overview of different generative models.
• Probabilistic models vs non-probabilistic models.
• Understanding of Variational Autoencoders (VAEs).
Week 11-12: Natural Language Processing (NLP)
• Introduction to NLP and its challenges.
• Language models and text generation.
• Case studies in NLP using generative models.
Week 13-14: Project: Generative AI Application (Submission)
• Apply Generative AI concepts.
• Students create a simple generative AI project.
Semester 2: Week 15 – 26
Note: Project work commences concurrently with classes starting from the 6th week.
Week 15-16: Recap and Introduction to Cloud Platforms and ML
• Recap of Introduction to Generative AI
• Overview of AWS services like S3, EC2, and SageMaker.for ML Beginners
• Basic Data Processing with AWS
Week 17-18: Generative Adversarial Networks (GANs)
• In-depth study of GANs.
• Training GANs and common challenges.
• Applications of GANs.
Week 19-20: Advanced GANs
• Deep dive into advanced GAN architectures.
• Conditional GANs and InfoGAN.
• StyleGAN and StyleGAN2.
Week 21-22: Transformers and Attention Mechanism
• Understanding transformer architecture.
• Attention mechanisms and their role.
• Applications in generative tasks.
Week 23-24: Transfer Learning in Generative AI
• Transfer learning techniques in generative tasks.
• Fine-tuning pre-trained models.
• Real-world applications and challenges.
Week 25-26: Ethical Considerations in Generative AI
• Discussing ethical concerns in AI and generative models.
• Bias and fairness in AI.
• Responsible AI practices.
Week 27-30: Final Project submission and Review
