Blogs
Long-form notes on the mathematics and mechanics behind diffusion models and deep learning, written while building the generative-AI projects in my CV.
Principles of Deep Learning
An overview of fundamental principles in deep learning, including backpropagation, gradient descent, and regularization techniques.
Read More
Overview of Diffusion Models
This article delves into Diffusion Models — a powerful class of generative models that has revolutionized the field of generative AI — exploring their core principles, theoretical foundations, and practical applications.
Read More
Advanced Diffusion Models
Mathematical foundations of diffusion models in depth: the flow matching framework, optimal transport, Schrödinger bridges, sampling techniques, and sophisticated solvers.
Read More
Diffusion Models: Probability Flow ODE and Probability Path
Connecting the continuous-time formulation of diffusion models to probability flow ODEs and the probability paths they trace.
Read More
From Variational Bayes to Diffusion Models
Tracing the mathematical thread connecting the intractable posterior of Bayesian statistics to the denoising objective at the heart of modern Diffusion Models.
Read More