Generative AI Mastery

A comprehensive journey from foundational machine learning concepts to advanced generative AI techniques and deployment strategies.

5
Modules
25+
Hours
15
Quizzes
5
Projects
Modules
Quizzes
Assignments
Capstone Project

Course Modules

1
Foundations of AI & Machine Learning
5 Lessons • 1 Quiz • 1 Assignment
20% Complete
  • Introduction to Machine Learning
    20 min • Video
    Completed
  • Supervised, Unsupervised, and Reinforcement Learning
    30 min • Reading
    Not started
  • Neural Networks & Deep Learning
    45 min • Video
    Not started
  • Training Neural Networks
    35 min • Video
    Not started
  • Module 1 Quiz
    15 min • 5 Questions
    Not started
2
Advanced AI Architectures
6 Lessons • 1 Quiz • 1 Assignment
0% Complete
  • Computer Vision Fundamentals
    40 min • Video
    Not started
  • Natural Language Processing
    45 min • Video
    Not started
  • Reinforcement Learning
    35 min • Video
    Not started
  • Module 2 Quiz
    15 min • 5 Questions
    Not started
3
Generative AI & LLMs
6 Lessons • 1 Quiz • 1 Assignment
0% Complete
  • Large Language Models (LLMs)
    50 min • Video
    Not started
  • Retrieval-Augmented Generation (RAG)
    45 min • Video
    Not started
  • Fine-Tuning LLMs
    40 min • Video
    Not started
  • Module 3 Quiz
    15 min • 5 Questions
    Not started
4
Optimizing & Deploying Gen AI Models
6 Lessons • 1 Quiz • 1 Assignment
0% Complete
  • Model Compression Techniques
    45 min • Video
    Not started
  • Model Training at Scale
    40 min • Video
    Not started
  • Deployment Strategies
    50 min • Video
    Not started
  • Module 4 Quiz
    15 min • 5 Questions
    Not started
5
Leveraging Gen AI for Real-World Applications
6 Lessons • 1 Quiz • 1 Assignment
0% Complete
  • Industry Use Cases
    35 min • Video
    Not started
  • Building End-to-End AI Products
    45 min • Video
    Not started
  • Module 5 Quiz
    15 min • 5 Questions
    Not started

Module 1: ML & Neural Network Fundamentals

15:00

1. Which of the following is an example of unsupervised learning?

2. What problem does high bias typically indicate?

Assignment 1: Building Your First Neural Network

3-4 hours 100 points Due: May 15, 2025

Objective

Implement a simple feedforward neural network for image classification using the MNIST dataset. This assignment will help you understand the fundamentals of neural network architecture, training process, and optimization techniques.

Tasks

  • 1
    Load and preprocess the MNIST dataset. Ensure proper normalization of pixel values and splitting into training and validation sets.
  • 2
    Build a neural network with: Input layer (784 neurons), Two hidden layers (128 & 64 neurons, ReLU activation), Output layer (10 neurons, softmax activation).
  • 3
    Train the model using gradient descent optimizer. Experiment with different learning rates and observe the impact on convergence.
  • 4
    Implement dropout regularization and compare model performance with and without regularization.
  • 5
    Analyze the bias-variance tradeoff in your model and document your findings.

Deliverables

  • Jupyter notebook with code and explanations
  • Performance comparison report (accuracy, loss curves)
  • 1-page reflection on bias-variance tradeoff observed

Submit Your Work

Drag and drop files here or click to browse

Accepted formats: .ipynb, .pdf, .zip (Max size: 50MB)

Final Capstone Project: Domain-Specific RAG Chatbot

20-25 hours 500 points Due: June 30, 2025

Objective

Build and deploy an end-to-end domain-specific RAG chatbot. This project integrates all the concepts learned throughout the course, from neural network fundamentals to LLM deployment.

Requirements

  • 1
    Data Preparation: Collect and preprocess domain-specific documents. Create an efficient embedding structure.
  • 2
    Model Implementation: Implement retrieval system with appropriate vector database. Fine-tune or prompt-engineer an LLM for your domain. Implement conversation memory.
  • 3
    Optimization: Apply at least two optimization techniques. Benchmark performance improvements.
  • 4
    Deployment: Create a user-friendly interface. Deploy your solution (cloud or local). Implement basic monitoring.
  • 5
    Evaluation: Test with at least 20 domain-specific queries. Compare performance with and without RAG. Document limitations and future improvements.

Deliverables

  • Complete codebase with documentation
  • Technical report (3-5 pages) explaining architecture and decisions
  • Demo video (3-5 minutes)
  • User feedback from at least 3 testers
  • Future improvements roadmap

Submit Your Project

Drag and drop files here or click to browse

Accepted formats: .zip, .pdf, .mp4 (Max size: 100MB)