GenAI Course - A Complete Course on Generative AI with Python
Welcome to this complete course on Generative AI (GenAI) with Python which includes many end-to-end projects. This course will teach you beginner topics like Python and advanced topics like LangChain. We are going to teach you Python from scratch and then move towards advanced topics. You will learn all the topics in Python and its ecosystem, which will enable you to develop end-to-end generative applications.
After learning Python and its ecosystem softwares you will start learning AI/ML topics necessary for building GenAI applications. So, this course is a complete course in Generative AI using the latest tools and technologies.
Course Objective:
The focus of this course is to build end to end GenAI applications. This course equips learners with the knowledge and practical skills to build Generative AI applications. In this course Python is used. So, developers will be using Python for the development of various GenAI projects. The course focuses on foundational concepts, NLP, deep learning, deep learning models, transformers, and hands-on implementation of GenAI projects.
There are a lot of examples and many end-to-end projects being developed throughout this project. End to end projects will help you learn and practise all the topics. This way students gain practical understanding.
Course Modules:
Module 1: Python and AI Foundations
- Getting Started with Python -
Installing Anaconda Python
and Visual Studio Code. Learn to write and Python code in Visual Studio Code.
- Python Essentials for AI (NumPy, Pandas, Matplotlib)
- Introduction to Jupyter Notebooks
- Introduction to Machine Learning Concepts
- Introduction to Deep Learning with TensorFlow and PyTorch
Module 2: Introduction to Generative AI
- What is Generative AI?
- Applications and Use Cases
- Difference between Discriminative vs Generative Models
- Ethical Concerns and Bias in Generative AI
Module 3: Neural Networks Essentials
- NLP in deep learning - Concepts like RNN, LSTM, Bidirectional RNN, Attention mechanism
-
Introduction to Neural Networks.
- Perceptrons and Multi-layer Perceptrons
- Backpropagation and Optimization
- Activation Functions
- Building Basic Neural Networks using Keras
Module 4: Generative Models Overview
- What are Generative Models?
- Autoencoders (AE)
- Variational Autoencoders (VAE)
- Generative Adversarial Networks (GANs)
- VAEs vs
GANs
Module 5: GANs in Depth
- GAN Architecture: Generator vs Discriminator
- Loss Functions in GANs
- Implementing GANs in TensorFlow or PyTorch
- Applications: Image Generation, Style Transfer
Module 6: Transformers and Language Models
- Intro to Transformers Architecture
- Attention Mechanism Explained
- Hugging Face Transformers Library
- Pre-trained Language Models: GPT, BERT, LLaMA, etc.
Module 7: Text Generation with Python
- Tokenization and Embeddings
- Text Generation using GPT-2/GPT-3 via API
- Prompt Engineering Basics
- Use Cases: Chatbots, Story Generation, Email Assistants
Module 8: Image, Audio and Video Generation
- Using Stable Diffusion / DALL·E with Python
- Generating Images from Text Prompts
- Intro to Music and Voice Generation with AI
- Tools: Diffusers, OpenAI API, Replicate API
- Text to video
generation on Google Colab
Module 9: Building GenAI Applications
- Using LangChain for LLM Orchestration
- Retrieval-Augmented Generation (RAG) with Python
- Creating a Document Q&A Chatbot
- Developing a Web App with Gradio or Streamlit
Module 10: Fine-Tuning and Deployment
- Fine-tuning LLMs with Custom Data
- Introduction to LoRA and PEFT
- Using Hugging Face Hub for Model Hosting
- Deploying GenAI apps to Cloud (Azure, AWS, GCP)
Module 11: Case Studies and Capstone Project
- Case Study: Content Creation Tool
- Case Study: Medical Report Generator
- Case Study: AI Coding Assistant
- Capstone Project: Build your own GenAI App
Tools & Frameworks Covered:
- Python, NumPy, Pandas, Matplotlib
- TensorFlow, Keras, PyTorch
- Hugging Face Transformers & Diffusers
- OpenAI API, LangChain, Streamlit, Gradio
- Weights & Biases, MLflow (optional)
Check more tutorials at AI Tutorials section.