Projects

Proof by Construction.

The public record: from-scratch machine learning, federated learning, and a connectomics flagship that ties biology to the swarm thesis. I build line by line — and then I share the code.

The project that started the thesis.

P1 · flagship

Brain Connectivity Matrix Super-Resolution

Recovering high-resolution brain wiring graphs from coarse connectomes — super-resolution for neuroscience.

Builds models that predict dense, precise neural-connectivity matrices from sparse, low-resolution observations; released the matrices as a public CC0 Kaggle dataset (289 downloads) so the community can build on them.

pythonjupyterconnectivity-matrix models

Recovering fine-grained wiring from coarse scans is the methodological bridge from neuroscience to multi-agent intelligence — and the dataset is public so the field can build on it.

The from-scratch library & applied work.

P2

Federated Learning with Logistic Regression

Private, distributed learning — training across data silos without moving the data.

A federated-learning implementation with a logistic-regression classifier: the on-ramp from classic ML to privacy-preserving, distributed training.

jupyterfederated patternlogistic regression

Training across data silos without centralizing the data — distributed coordination that answers real privacy constraints.

P3

Ridge · Lasso · ElasticNet — From Scratch

Regularized linear models written line-by-line from first principles.

From-scratch implementations of Ridge, Lasso and ElasticNet regression — no libraries for the core math.

pythonjupyternumpy-level math

Built from scratch — Ridge, Lasso, ElasticNet, gradient descent, Bayes — so every model is inspectable.

P4

Gradient Descent vs SGD — From Scratch

The optimizer battle, implemented by hand for linear regression.

Side-by-side from-scratch gradient-descent vs stochastic-gradient-descent implementations, showing the bias/variance computation trade-off.

pythonjupyter

Optimization is the micro-mechanism of learning — the update rule that decides how a model actually learns.

P5

Binary Bayes Classifier — From Scratch

A probabilistic classifier built from the fundamentals of Bayesian inference.

Binary Bayes classifier written from scratch — no off-the-shelf estimation.

pythonjupyter

Applied mathematics first: where the optimization habit started.

P6

TSP with a Genetic Algorithm

Combinatorial optimization via evolutionary search.

Solves the Traveling Salesman Problem using a genetic algorithm — the earliest public hint of population-based, emergent problem solving.

python

Evolutionary and population-based search — my first love in AI, still my favorite tool for hard optimizations.

P7

Bank Customer Churn Prediction

Applied predictive modeling on a real business problem.

Customer-churn prediction on banking data — representative of my commercial data-science work.

jupyterscikit-learn stack

Predictive modeling as production work — the notebook-to-service path that mirrors real deployment.

P8

Morgan Algorithm — Unique Atom Numbering

Graph-theoretic canonical numbering of atoms in molecules.

Implements the Morgan unique-atom-numbering algorithm for molecular graphs — chemistry + graph theory + code.

python

Graph-theoretic chemistry — canonical atom numbering that ties molecular structure to computation.

Every one of these was built from the inside out — I trust a model only when I can see inside it. That discipline is what I bring to agent systems: orchestration, tool use, memory, and evaluation, all built on the same implementation depth.

Let's Build

Let's build the next layer of intelligence — together.

Start a Conversation
Let's talk!