Generative AI

₹9,900.00 (Inc. GST)

Centre for Summer Training

Batch Date

Clear

SKU: N/A Category: Summer Training Program

Generative AI is an exciting and rapidly growing field of artificial intelligence that focuses on creating new data similar to existing datasets. This course introduces participants to the fundamental concepts, techniques, and tools required to build and implement generative models. Students will explore various approaches such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Diffusion models. The course strikes a balance between theoretical knowledge and practical implementation, providing participants with hands-on experience in developing and deploying generative models in real-world scenarios.

Pre-Requisites:

Basic knowledge of computer operations
Familiarity with high-school level mathematics (basic algebra, probability)
Basic understanding of programming, preferably in Python

Key Learning Outcomes:

By the end of this course, participants will:

Understand the foundational concepts of Generative AI and its various applications, including image generation, text generation, and data augmentation.
Be able to differentiate between various generative models such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Diffusion models.
Gain hands-on experience in implementing and experimenting with basic generative models using Python and popular AI frameworks like TensorFlow and PyTorch.
Learn how to evaluate and fine-tune generative models for specific tasks, such as image creation or text synthesis.
Understand ethical considerations and challenges associated with Generative AI, such as bias, misinformation, and content manipulation.

Target Audience:

Beginners who are interested in AI and its generative capabilities
Students and professionals from non-technical backgrounds looking to gain foundational knowledge in Generative AI
Individuals interested in enhancing their skills for career opportunities in AI

Test & Evaluation:

Assignments: Throughout the course, participants will complete practical assignments to reinforce learning.
Final Assessment: A final evaluation will be conducted to assess participants’ understanding and application of course material.

Certification:

Successful participants will receive a Certificate of Completion.
A Project Letter will be awarded upon the successful completion of the project.
Students who leave the course midway or do not complete it will not receive any certification.

Delivery Mode & Duration:

Mode: Online Live Sessions
Duration: 120 Hours (60 Hours of Online Live Sessions + 60 Hours of Assignments)

Additional information

Centre for Summer Training	IIT Kanpur Campus, Online Live
Batch Date	Batch 1, Batch 2

Curriculum

Module 1: Introduction to Generative AI

What is Generative AI?
Historical Context and Evolution of AI
Applications of Generative AI in Various Industries
Overview of Generative Models (GANs, VAEs, Diffusion Models, etc.)
Ethical Considerations in Generative AI

Module 2: Fundamental Concepts in AI

Basic AI and Machine Learning Concepts
Introduction to Neural Networks
Understanding Probability and Statistics in AI
Overview of Deep Learning

Module 3: Generative Adversarial Networks (GANs)

Introduction to GANs
How GANs Work: Generator and Discriminator
Training GANs: Loss Functions, Optimization Techniques
Hands-on: Implementing a Simple GAN in Python using TensorFlow/PyTorch
Advanced GAN Architectures (DCGAN, WGAN, etc.)
Common Issues and Troubleshooting in GAN Training

Module 4: Variational Autoencoders (VAEs)

Introduction to Autoencoders
What Makes VAEs Different?
Mathematical Foundation of VAEs
Hands-on: Implementing a Simple VAE in Python
Applications of VAEs in Data Generation

Module 5: Diffusion Models and Other Generative Techniques

Introduction to Diffusion Models
Comparison with GANs and VAEs
Hands-on: Implementing a Basic Diffusion Model
Overview of Other Generative Models (e.g., Flow-based Models, Transformers)

Module 6: Practical Applications and Case Studies

Generative AI in Art and Creativity
Generative AI in Text Generation (GPT, BERT)
Case Studies: Real-world Applications of Generative AI
Hands-on: Building a Simple Text Generator using GPT

Module 7: Fine-Tuning and Evaluating Generative Models

Fine-Tuning Pre-trained Generative Models
Metrics for Evaluating Generative Models (FID, IS, etc.)
Hands-on: Fine-tuning and Evaluating a GAN or VAE
Best Practices in Model Deployment

Module 8: Final Project and Course Wrap-up

Final Project: Creating and Presenting a Generative Model
Course Recap and Review
Discussion on Future Trends in Generative AI
Q&A and Feedback Session

All Courses

Generative AI

Pre-Requisites:

Key Learning Outcomes:

Target Audience:

Test & Evaluation:

Certification:

Delivery Mode & Duration:

Additional information

Curriculum

Module 1: Introduction to Generative AI

Module 2: Fundamental Concepts in AI

Module 3: Generative Adversarial Networks (GANs)

Module 4: Variational Autoencoders (VAEs)

Module 5: Diffusion Models and Other Generative Techniques

Module 6: Practical Applications and Case Studies

Module 7: Fine-Tuning and Evaluating Generative Models

Module 8: Final Project and Course Wrap-up

Enquiry

All Courses

Generative AI

Pre-Requisites:

Key Learning Outcomes:

Target Audience:

Test & Evaluation:

Certification:

Delivery Mode & Duration:

Additional information

Curriculum

Module 1: Introduction to Generative AI

Module 2: Fundamental Concepts in AI

Module 3: Generative Adversarial Networks (GANs)

Module 4: Variational Autoencoders (VAEs)

Module 5: Diffusion Models and Other Generative Techniques

Module 6: Practical Applications and Case Studies

Module 7: Fine-Tuning and Evaluating Generative Models

Module 8: Final Project and Course Wrap-up

Enquiry

Related products