Course Content

​

Week 1: Introduction to Generative AI

• What is Generative AI?

  • Definition and Scope

  • Historical Development of Generative AI

  • Applications of Generative AI in Different Domains

• Overview of Popular Generative Models

  • GPT (Generative Pre-trained Transformer)

  • Variational Autoencoders (VAEs)

  • Generative Adversarial Networks (GANs)

• Practical Session: Setting Up Environment and Tools

  • Installation and Configuration of AI Frameworks (e.g., TensorFlow, PyTorch)

  • Introduction to AI Development Platforms (e.g., OpenAI, Hugging Face)

Week 2: Understanding Transformers and Language Models

• Basics of Transformer Architecture

  • Attention Mechanism

  • Encoder-Decoder Architecture

• How Language Models Work

  • Pre-training and Fine-tuning

  • Understanding Tokenization and Embeddings

• Practical Session: Experimenting with Pre-trained Models

  • Using GPT and BERT Models

  • Fine-tuning a Pre-trained Language Model

Week 3: Introduction to Prompt Engineering

• What is Prompt Engineering?

  • Definition and Importance

  • Role of Prompts in Generative AI

• Basic Techniques for Crafting Prompts

  • Understanding Context and Intent

  • Using Keywords and Phrases

• Practical Session: Crafting and Testing Simple Prompts

  • Generating Text Based on Basic Prompts

  • Analyzing Model Outputs

Week 4: Advanced Prompt Engineering Techniques

• Advanced Prompting Strategies

  • Controlling Output Length and Style

  • Managing Temperature and Diversity Parameters

• Prompting for Different AI Tasks

  • Text Completion

  • Question Answering

  • Text Classification

• Practical Session: Developing Complex Prompts

  • Creating Prompts for Specific Use Cases

  • Fine-tuning Prompts for Desired Outcomes