My paper summaries
Plain-language write-ups of my five papers — the problem, what I did, and what came out.
Research notes
Blog
Research notes and explainers, organised into sections. Pick a topic below.
A working notebook on my research and the machine learning behind it: summaries of my own papers and the related work I build on, short explainers for the core algorithms, and the mathematics underneath them — written to be readable without a machine-learning background.
Other papers I build on
Short notes on the external work my methods extend or compare against (CTGAN, GAIN, transformers, …).
Algorithms, explained
One-paragraph explainers for the building blocks: trees, MLPs, LSTMs, autoencoders, GANs, attention, fusion.
Mathematical foundations
The recurring equations — softmax, cross-entropy, gradient descent, the GAN objective, KL/JS, ROC/AUC, recall@k.
Glossary
Quick definitions for the terms used across the papers and notes.
Reading list
The books, courses and sites I point people to for the full version.