Admissions Open for JANUARY Batch

UPMENTA COURSES IMAGES (16)

Understand VAEs and GANs for creating new data from mathematical models.

Days : Tue & Thu

Duration : 3 Hours

Timings: 8 - 10 PM IST

Try Risk-free, 15 Days Money Back Guarantee

3 Hours

9 - 10 PM IST

Tue & Thu

Maths for Generative Models

Understand VAEs and GANs for creating new data from mathematical models.

Online Live Instructor-Led Learning

3 Hours

8 - 10 PM IST

Tue & Thu

By end of this course

Get stronger in

Variational Autoencoder loss functions

GAN training and discriminator math

Get familier with

Latent space representation

Optimal transport concepts in generation

New Batch Starts : jan 2026

Limited seats only 15 students per batch

Who Should Enroll?

This course is for learners aiming to understand the mathematical foundations of generative modeling, including probability distributions, latent spaces, and optimization, tailored for those pursuing domain expertise in generative AI.

Prerequisites

Probability, optimization, and deep learning math.

Experience our course risk-free

We offer a 15-day money back guarantee

Prerequisite

Probability, optimization, and deep learning math.

Who Should Enroll?

This course is for learners aiming to understand the mathematical foundations of generative modeling, including probability distributions, latent spaces, and optimization, tailored for those pursuing domain expertise in generative AI.

By the end of this course

Get Stronger in

  • Variational Autoencoder loss functions
  • GAN training and discriminator math

Get Familiar in

  • Latent space representation
  • Optimal transport concepts in generation

What you will learn

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Ut elit tellus, luctus nec ullamcorper mattis, pulvinar dapibus leo.

Course Contents

Day 1 - Linear Algebra Fundamentals

Topics

  • Latent variable models
  • Evidence Lower Bound (ELBO) derivation
  • Reparameterization trick math

Key Outcomes

Understand and implement VAEs

Day 2 - Generative Adversarial Networks (GANs)

Topics

  • Min–max optimization formulation
  • Jensen-Shannon divergence math
  • Gradient dynamics in adversarial training

Key Outcomes

Build and optimize GAN architectures

Day 3 - Optimal Transport & Wasserstein

Topics

  • Latent variable models
  • Evidence Lower Bound (ELBO) derivation
  • Reparameterization trick math

Key Outcomes

Understand and implement VAEs

Day 1 - Linear Algebra Fundamentals

Topics

  • Latent variable models
  • Evidence Lower Bound (ELBO) derivation
  • Reparameterization trick math

Key Outcomes

Understand and implement VAEs

Day 2 - Generative Adversarial Networks (GANs)

Topics

  • Min–max optimization formulation
  • Jensen-Shannon divergence math
  • Gradient dynamics in adversarial training

Key Outcomes

Build and optimize GAN architectures

Day 3 - Optimal Transport & Wasserstein

Topics

  • Latent variable models
  • Evidence Lower Bound (ELBO) derivation
  • Reparameterization trick math

Key Outcomes

Understand and implement VAEs