Always learning
click me

Exploring the mathematics of intelligence

I'm Gaurav Bhowmick — a student of quantitative methods, artificial intelligence, and machine learning. This is where I document what I'm learning, building, and questioning.

Machine Learning
Statistics
Neural Networks
Stochastic Processes
Reinforcement Learning
Information Theory
Optimal Transport
01

About

generating profile
I'm endlessly curious about how intelligence works — both the kind that emerges from neural architectures and the kind encoded in statistical theory built over centuries.

This site is my public notebook: a place to explore ideas, visualize concepts, and share what I'm figuring out. I think in distributions, not averages.

I'm drawn to the elegance of optimal transport theory, the surprising depth of attention mechanisms, and the practical beauty of well-calibrated models.

I'm not here as an expert — I'm here as a student who believes the best way to learn is to build and share.
Explore my interests
Click nodes to explore · Drag to pan
Knowledge Map

Click a node to explore

This graph maps the topics I'm studying and how they connect. Each node is an area of curiosity, and the edges represent how these ideas flow into each other. Nothing exists in isolation — that's what makes this fun.

Learning journey
2024

Foundation

Fell down the probability rabbit hole

Started seriously studying measure-theoretic probability and stochastic calculus. Built my first Monte Carlo simulations and realized how beautiful randomness can be when you give it structure.

ProbabilityMonte CarloStochastic Calculus
2024

Deep Dive

Discovered Optimal Transport

Read Villani's "Topics in Optimal Transportation" and was hooked. Started implementing Wasserstein distance computations and Sinkhorn algorithms. Applied clustering methods to time series regime detection.

WassersteinSinkhornClustering
2025

Architecture

Deconstructing transformers, layer by layer

Spent months understanding attention mechanisms from first principles. Built visualizations of how LLMs process multimodal inputs — from image patches to token embeddings. Created an explainer video series breaking down the inference pipeline.

TransformersAttentionMultimodalLLMs
2025

Generative

Exploring diffusion models and flow matching

Studied the mathematical connections between score-based diffusion, denoising, and flow matching. Implemented toy diffusion models to build intuition for how noise becomes signal.

DiffusionScore MatchingFlow
NOW

Current

Building my public learning lab

Launched this site as a home for interactive explorations. Currently studying reinforcement learning from human feedback, information geometry, and the intersection of optimal transport with generative models. @Marginator on X for data-driven takes with edge.

RLHFInfo Geometry@Marginator
02

Interactive Lab

Play with live visualizations. Drag sliders, click to interact — these aren't screenshots, they're running code.

Neural Network

Interactive
Watch activations flow through layers. Adjust architecture in real-time.
3
5

Gradient Descent

Click to place
Click anywhere to drop a ball. Watch it find the minimum.
0.08
0.5

Distribution Morphing

Optimal Transport
Watch one probability distribution morph into another via optimal transport.
0.00
Gauss
Bimod

Attention Heatmap

Transformer
Hover tokens to see self-attention weights. Adjust temperature.
1.0
1

Brownian Motion

Stochastic
Geometric Brownian motion paths — the backbone of stochastic calculus.
0.10
0.02
03

Explorations

Notes, experiments, and deep dives. Learning in public.

Let's explore together

I'm always looking for interesting conversations about AI, quantitative methods, and the ideas that sit between disciplines.

All views and content on this site are entirely my own. They represent personal learning and exploration, and are not affiliated with, endorsed by, or representative of any employer, organization, or institution.