Skip to content
View ivarick's full-sized avatar

Block or report ivarick

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ivarick/README.md
Typing SVG
   

Independent AI researcher. No lab, no supervisor — just a machine and a research agenda.

My work sits at the intersection of neural signal processing, non-standard data modalities, and ML systems under real hardware constraints. I compete in ML challenges as a forcing function for depth, not rankings.

Recent work also includes IMAGINE, a cross-domain MEG decoding pipeline for mental imagery that combines localizer-to-imagery transfer, temporal search, and complementary MEG feature branches.


What I Work With

Signal Processing    →   MEG/EEG · Riemannian geometry · CSP · Xdawn · MNE
Deep Learning        →   PyTorch · Transformers · Diffusion · EEGNet
Classical ML         →   XGBoost · LightGBM · Stacking · Bayesian optimization

Languages & Libraries

Python C# PyTorch scikit-learn NumPy Pandas XGBoost LightGBM MNE pyRiemann Unity


Selected Projects

Project What it is
🧠 IMAGINE Cross-domain MEG decoding of mental imagery with LDA + prototype matching, built as a research-style pipeline
🌌 MALLORN TDE detection from astronomical lightcurves — physics-informed features + semi-supervised ensembling
Chess Transformer Engine Move prediction via self-attention trained on 2M PGN games
🔥 Wildfire Monitoring Multi-stage fire prediction pipeline integrating satellite + sensor data

Background

Before AI research, I spent several years in game development — building games and systems in Unity with C#. That background shaped how I think about real-time systems, optimization under constraints, and building things that actually run on real hardware. It's also where I developed an intuition for debugging complex, stateful systems — which transfers directly into ML pipelines.


Research Interests

Brain-Computer Interfaces   Neuroscience-inspired architectures   Predictive coding   Non-standard modalities   Continual learning   Small-model optimization   Astronomical ML


All experiments run locally. Results over performance theater.

Pinned Loading

  1. Human-Mental-Imagery-from-Brain Human-Mental-Imagery-from-Brain Public

    The IMAGINE project focuses on decoding human mental imagery from brain activity using Magnetoencephalography (MEG).

    Python

  2. MALLORN-Transient-Detection MALLORN-Transient-Detection Public

    MALLORN: Automated detection of Tidal Disruption Events (TDEs) from synoptic sky surveys.

    Python

  3. AI-Based-Wildfire-Monitoring-System AI-Based-Wildfire-Monitoring-System Public

    FireWatch is an end-to-end, multi-stage system for predicting and monitoring wildfires, leveraging AI, 5G connectivity, and renewable energy to deliver a fully integrated, real-time operational sol…

    Python

  4. Chess-Transformers-Engine Chess-Transformers-Engine Public

    chess engine using the transformers architecture

    Python 1

  5. Sentiment-Analysis-Transformer-Model Sentiment-Analysis-Transformer-Model Public

    IMDB reviews Sentiment Analysis Transformer Model

    Python

  6. Harry-Potter-Style-Novel-Generator Harry-Potter-Style-Novel-Generator Public

    A character-level GPT language model in PyTorch, trained on Harry Potter books to generate fanfiction-style chapters and scenes interactively.

    Python