The Story

Behzat Aslanoğlu

From molecules to neurons to agents

Mathematics and code grew up in my head together — then moved through molecules, brains, and machine learning to the frontier: LLMs, agentic AI, and swarms of agents. One unbroken thread.

80
citations
4
h-index
3
i10-index
5
papers
23
repos

citation counts as reported on Google Scholar at time of verification

// the story

The parallel arc.

Mathematics, code, computer science, and the web grew up in my head together — each sharpening the others. I earned a BSc in Applied Mathematics (University of Tabriz), an MSc in Applied Informatics at Istanbul Technical University (3.94/4.00 GPA), and a PhD candidacy in Information & Communication Engineering there — while simultaneously teaching myself to program and to think in machine learning. The math informed the code; the code made the math real.
The discipline was never about memorizing formulas — it was about decomposing a messy, real problem into equations you can actually solve. Differential equations, linear algebra, and probability became the grammar I read every dataset and network in, while the compiler was the pencil I used to test the sentences. That single thread — from abstract proof to working software — runs from molecular simulations to LLM agents.

Math never waited for the code, and the code never waited for the math. They arrived together and stayed together — one continuous, intertwined thread from the very start.

the through-line · BSc → MSc → PhD → the work

The discipline was never about memorizing formulas — it was about decomposing a messy, real problem into equations you can actually solve.

applied mathematics · University of Tabriz

Don't just fit the curve — model the mechanism.

molecular dynamics · TÜBİTAK, F876L resistance story

Vision

Intelligence from molecules to neurons to agents — one unbroken thread. Mathematics, science, and agentic AI grown together, and shared as I build.

Mission

Build LLMs and agentic AI that don't just answer — they act. From first-principles ML to coordinated swarms of agents, ship systems, not notebooks.

Philosophy

Reduce a messy, real system to a model you can trust. Respect the physics, model the mechanism — don't just fit the curve. Math and code arrived together and never waited for each other.

The Goal

Coordinated swarms where emergence echoes the brains I studied — resilience, parallel exploration, and answers that come from collective reasoning rather than one model's guess.

The Engine

Three Chapters, One Thread

The pillars the story runs on — and the engine I still build with.

01

From Proofs to Physics

The Mathematician & Scientist

Applied mathematics, molecular dynamics, and the F876L resistance story. The discipline of decomposing a messy, real problem into equations you can actually solve.

02

Connectomics as Graph Theory

The Neuroscientist

Super-resolution for the most complex known graph — predicting high-resolution brain graphs from sparse, noisy observations. Open data, released to the community.

03

From ML to Swarms

The Agent Builder

From-scratch ML → federated learning → agents. Today: LLM systems end to end, and a working thesis that emergence echoes the brains I studied.

Let's talk!