10
Lessons
40 Hours
Duration
English
Language
Share This Class:
Course features:
- Practical hands on
- Lab sessions
- Training by experienced faculty
PRE-REQUISITES:
- Basic understanding of Python programming
- Familiarity with machine learning concepts (recommended)
Lab setup:
- Cloud services Google Colab
- Anaconda Python
- Python library like Numpy, Pandas, Matplotlib, Tensorflow etc
Learning Path
- What is Generative AI?
- Why Generative AI?
- Generative AI Principles
- Types of Generative Models
- Machine Learning Algorithms with Generative AI
- Applications of Generative AI
- Generative AI: Advantages and Disadvantages
- Ethical Considerations
- Google Colab Introduction
- Summary and Conclusion
- Introduction to Python
- Data types
- Data structures
- Mutable and Immutable Data Structures
- List, Subscripting, Nested List
- Tuple, Use cases
- String Manipulation
- Dictionary
- Control flow
- Functions
- Hands on Session
- Summary and Conclusion
- Modules
- User Define Modules
- using import
- using from
- Built In Modules
- Object Oriented Programming
- Classes and Objects
- The “self” keyword
- Methods and Attributes
- Constructor
- Object Variable and Class Variable
- Class Inheritance
- Hands on Session
- Summary and Conclusion
- NumPy for numerical operations
- Pandas for data manipulation and analysis
- Handling and preparing data for generative models
- Hands on Session
- Summary and Conclusion
- Basics of TensorFlow for building models
- Keras as a high-level API for neural networks
- Installing and setting up the environment
- TensorFlow Programming
- Hands on Session
- Summary and Conclusion
- Basics of GAN architecture
- Building and training a simple GAN
- Common challenges and solutions
- TensorFlow’s Python API
- Use TF-GAN Estimators to quickly train a GAN
- Hands on Session
- Summary and Conclusion
- Introduction to autoencoders
- Variational inference and VAEs
- Building and training VAEs
- Autoencoder Demo
- Train the basic autoencoder
- Hands on Session
- Summary and Conclusion
- Building conditional generative models
- Applications in image synthesis and manipulation
- Combining GANs and VAEs
- Hands on Session
- Summary and Conclusion
- Neural style transfer
- Image generation using generative models
- Creative applications of generative models
- Hands on Session
- Summary and Conclusion
- Introduction to language models
- Text generation using GPT-3 and other models
- Building chatbots and conversational agents
- Hands on Session
- Summary and Conclusion