Admissions Open for JANUARY Batch

UPMENTA COURSES IMAGES (14)

Learn mathematical concepts for graph data and network analysis.

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

Graph Machine Learning

Learn mathematical concepts for graph data and network analysis.

Online Live Instructor-Led Learning

3 Hours

8 - 10 PM IST

Tue & Thu

By end of this course

Get stronger in

Graph Laplacians and adjacency matrices

Message passing mechanics in GNNs

Get familier with

Node embedding methods

Graph regularization and connectivity

New Batch Starts : jan 2026

Limited seats only 15 students per batch

Who Should Enroll?

This course is for learners interested in applying mathematical principles to graph-based problems in social networks, biological systems, or recommendation engines—ideal for those pursuing specialized AI expertise

Prerequisites

Basic linear algebra and graph theory concepts.

Experience our course risk-free

We offer a 15-day money back guarantee

Prerequisite

Basic linear algebra and graph theory concepts.

Who Should Enroll?

This course is for learners interested in applying mathematical principles to graph-based problems in social networks, biological systems, or recommendation engines—ideal for those pursuing specialized AI expertise

By end of this course

Get Stronger in

  • Graph Laplacians and adjacency matrices
  • Message passing mechanics in GNNs

Get Familiar in

  • Node embedding methods
  • Graph regularization and connectivity

Course Contents

Day 1 - Graph Basics

Topics

  • Adjacency matrices and Laplacians
  • Degree and normalized Laplacians
  • Spectral decomposition of graphs

Key Outcomes

Build mathematical foundation for GNNs

Day 2 - Graph Neural Networks (GNNs)

Topics

  • GCN layer derivation
  • Message passing math
  • Graph convolution as spectral filtering
  • Normalization tricks

Key Outcomes

Derive and train graph based models

Day 3 - Variational Inference

Topics

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

Key Outcomes

Understand and implement VAEs

Day 1 - Graph Basics

Topics

  • Adjacency matrices and Laplacians
  • Degree and normalized Laplacians
  • Spectral decomposition of graphs

Key Outcomes

Build mathematical foundation for GNNs

Day 2 - Graph Neural Networks (GNNs)

Topics

  • GCN layer derivation
  • Message passing math
  • Graph convolution as spectral filtering
  • Normalization tricks

Key Outcomes

Derive and train graph based models

Day 3 - Variational Inference

Topics

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

Key Outcomes

Understand and implement VAEs