MiniGPT-M4
A compact language-model study exposing Transformer internals through a custom BPE tokenizer, PyTorch components and local Apple Silicon training experiments.
RESEARCH / EXPERIMENTS / COMPETITIONS
Research and competitions
Model architectures, data preparation, scientific research tools and competition experiments. Outcomes are presented alongside the conditions and limitations behind them.
Software contributions to healthcare research
The Tanita and OSAS work is connected through document extraction, data preparation and tabular modeling, while retaining separate processing workflows. The EEG/ALS toolkit addresses signal streams and experimental communication research. Patient records, EEG recordings and unauthorized datasets are not included on this site.
OSINT Framework
A modular prototype organizing authorized open-source investigations through plugin scans, persistent jobs, an API, live progress and optional worker processes.
Tanita Report Extractor
Private document-processing prototype exploring local PDF-to-table extraction through batch processing and a desktop interface, with explicit privacy boundaries.
EEG & ALS Research Toolkit
Private research toolkit exploring EEG, signal features and classical machine learning through desktop, offline and local web components.
Sleep Apnea Risk Research
Private logistic-regression research experiment exploring binary classification, ROC visualization and explicit input validation for tabular data.
ING Türkiye Datathon
A competition archive combining time-window customer features, boosting models, ensemble blending and Optuna experiments for customer-behavior modeling.
Turkish Address Research
A research collection exploring noisy Turkish-address normalization and task-specific label prediction through text methods, vector retrieval and geographic approaches.
Trendyol Hackathon
Trendyol Hackathon work represented among competition experiences, without extending the supplied technical scope, team role or outcome details.
Machine Learning Notebook Archive
A source-cataloged archive of 33 independent notebooks exploring machine-learning ideas across image, text, audio and tabular data tasks.
How to read the experiment collections
Notebooks in AI-Projects and the Turkish address experiments remain sub-studies within their parent collections. The same work is not counted as a separate achievement on different pages. Participation does not imply a verified ranking or award, and unrecorded performance figures are not added.