Reproducibility 4 min read
One confirmatory endpoint for postural sway
Why this reanalysis keeps a single displacement contrast, and what the other analysis families did not support.
Read noteThe reasoning
behind the research.
Short notes on methods, evaluation, reproducibility, and engineering. Dates and references are explicit; claims tied to a paper return to its source record.
11 of 11 notes
11 research notes
Subscribe via RSSReproducibility 3 min read
Cold-start evaluation: identities before architectures
Why identity-disjoint splits, paired deltas, and an explicitly incomplete evidence grid matter more than an impressive model diagram.
Read noteReproducibility 9 min read
ECG classification: evaluation before architecture
Patient leakage, imbalance, uncertainty, and other decisions that matter before selecting a model.
Read noteInterpretable ML 7 min read
Post-hoc explanations and intrinsically interpretable models
A practical distinction between explaining a fitted black box and designing a model whose structure is inspectable.
Read noteMethods 8 min read
The kernel trick, revisited for biomedical data
A compact explanation of kernels, inductive bias, and why small-data settings still reward careful similarity design.
Read noteRisk-aware learning 7 min read
CVaR, Value-at-Risk, and the tail that matters
A methods note on threshold risk, expected tail loss, and why evaluation assumptions matter.
Read noteMethods 8 min read
LSTM or GRU? Start with the protocol
Architecture differences matter less than leakage control, baselines, horizons, and repeated evaluation.
Read noteInterpretable ML 3 min read
Interpretability by design with Formal Concept Analysis
How structured constraints can keep a clinical-risk model inspectable, plus the validation still needed before deployment.
Read noteBiomedical AI 3 min read
Quantum-inspired kernels for scarce ECG labels
A research note on similarity geometry, patient-wise evaluation, and what the QADK study does—and does not—show.
Read noteRisk-aware learning 3 min read
Risk-aware reinforcement learning beyond average return
Why sequential decision systems need explicit downside objectives and skeptical backtesting.
Read noteResearch engineering 8 min read
Reproducible Python environments for ML experiments
A current, framework-neutral setup checklist built around isolated environments, locked dependencies, smoke tests, and official install selectors.
Read noteNo matches this time.
Try a broader search or a different topic.