Projects

A selection of projects across research, applied machine learning, scientific computing, and technical tooling. Rather than listing everything, I prefer to highlight projects that reflect different parts of my profile: adaptive learning systems, sensing, scientific software, and computational modeling.

Additional projects

Applied deep learning

code128-net

Deep learning for localization of Code128 finder patterns from normalized one-dimensional signals, developed in an applied industrial setting.

View repository

Neuromorphic learning

Spiking Neural Network Experiments

Experimental work on spiking neural networks, with attention to STDP, reward-modulated learning, and neuromorphic computation.

View repository

Scientific dashboards

Cosmic Rays Live Dashboard

A real-time dashboard-oriented project for monitoring and publishing data from a particle physics detector.

View repository

Quantitative modeling

Volatility Carry Modeling

A project on modeling implied volatility through multi-factor statistical approaches, reflecting part of my background in quantitative analysis.

View repository

Astrophysical modeling

Binary Black Hole Delay-Time Modeling

Computational work on delay-time distributions and related modeling questions in binary black hole systems.

View repository

Networks and systems

Vehicular Network Dynamics

A project on vehicular networks exploring communication, coordination, and system-level behavior in distributed settings.

View repository

C++ and scientific computing

C++ Particle Reconstruction

Scientific computing work in C++ focused on particle reconstruction and data-processing pipelines.

View repository

Theory and machine learning

Information Bottleneck Explorations

Experiments and computational explorations related to the information bottleneck perspective in machine learning.

View repository

Perspective

Across these projects, recurring themes include adaptive computation, efficient learning systems, sensing and data-driven modeling, scientific software, and machine learning under practical constraints.