Turning thinking into distribution
Notes, summaries, build logs, and essays. Some are finished; several are drafts in the queue. Writing is how I compound and share what the research produces.
Why prediction accuracy is not enough for physical systems
A test-set number is a weak proxy for engineering value. What a model enables matters more than the metric it improves.
Read noteWhat makes a surrogate model useful in engineering?
Speed is the obvious draw, but usefulness is set by reliability, calibration, and fit with an existing workflow.
Draft · coming soonFailure modes in ML for physical simulations
A working catalogue of how learned models break: extrapolation, spectral bias, error accumulation, and silent confidence.
Draft · coming soonA map of machine learning for structural dynamics
An attempt to organise the landscape: methods, problem types, and where learned models currently earn their place.
Draft · coming soonNotes from papers on surrogate modelling
Running notes on surrogate modelling literature — what is claimed, what is shown, and what is assumed.
Draft · coming soonScientific ML: where physics still matters
Where physics-based structure remains essential, and where data-driven methods genuinely add value.
Draft · coming soonBuilding a baseline surrogate model
Setting up a dataset, a baseline, and an evaluation harness before reaching for anything clever.
Draft · coming soonDesigning a research workflow system
Turning scattered papers, notes, and experiments into a structured, reusable research log.
Draft · coming soonLessons from early technical prototypes
What the first rough prototypes taught me about scope, evaluation, and knowing when to stop.
Draft · coming soonThe gap between research novelty and product value
Novelty is rewarded in research and irrelevant in products. The bridge between the two is reliability and fit.
Draft · coming soonHow deeptech research becomes intellectual property
The path from a research result to a defensible technical asset — and where it usually breaks down.
Draft · coming soonBuilding technical moats as a young researcher
Compounding depth, proof-of-work, and reusable assets as a deliberate long-term strategy.
Draft · coming soon