Generative AI
•Course Title: Introduction to Generative AI
**Course Overview:**
This online course aims to provide a comprehensive introduction to Generative AI, covering fundamental concepts, models, and applications. Participants will gain hands-on experience in implementing and working with generative models, exploring both theoretical foundations and practical applications.
**Week 1: Introduction to Generative AI**
- Overview of Generative AI
- Historical development and key milestones
- Importance and applications in various fields
**Week 2: Probability and Statistics Foundations**
- Probability theory for generative modeling
- Statistical concepts and distributions
- Maximum Likelihood Estimation (MLE) and Bayesian methods
**Week 3: Neural Networks Basics**
- Introduction to neural networks
- Feedforward and backpropagation
- Activation functions and architectures
**Week 4: Introduction to Generative Models**
- Discriminative vs. Generative models
- Types of generative models: autoregressive, variational autoencoders (VAEs), and generative adversarial networks (GANs)
- Case studies and examples
**Week 5: Autoregressive Models**
- Autoregressive models and their applications
- PixelRNN and PixelCNN
- Training and generation with autoregressive models
**Week 6: Variational Autoencoders (VAEs)**
- Introduction to VAEs
- Encoder and decoder architecture
- Training and sampling from VAEs
**Week 7: Generative Adversarial Networks (GANs)**
- Introduction to GANs
- GAN architecture: generator and discriminator
- Training and optimization of GANs
**Week 8: Advanced Topics in Generative AI**
- Conditional generation
- Style transfer and domain adaptation
- Transfer learning and fine-tuning generative models
**Week 9: Evaluation Metrics and Challenges**
- Evaluation metrics for generative models
- Challenges in training and evaluating generative models
- Ethical considerations in Generative AI
**Week 10: Applications of Generative AI**
- Image generation and synthesis
- Text generation and language models
- Creative applications and industry use cases
**Week 11: Future Trends and Research Directions**
- Current research trends in Generative AI
- Open challenges and areas for improvement
- Future directions and potential breakthroughs
**Week 12: Capstone Project**
- Apply knowledge gained throughout the course to complete a generative AI project
- Showcase and discuss projects in the final class session
**Prerequisites:**
- Basic understanding of machine learning concepts
- Familiarity with Python programming language and popular machine learning libraries such as TensorFlow or PyTorch.
**Assessment:**
- Weekly quizzes
- Midterm project
- Final capstone project
**References:**
- "Generative Deep Learning" by David Foster
- "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
- Research papers and online resources provided during the course.
**Note:**
The syllabus is subject to adjustments based on the pace of the class and emerging developments in the field of Generative AI.
Major Projects
Chatbot using Deep Learning
Recommender System
Human Body Activity Recognition
Text Generation
Image to Text generation