WEEK 17 · PAPER 2 EXPERIMENTS, COMPLETE
A clinical trial is not "we gave the drug to some people and they felt better". It is arms, doses, randomisation, repeats, and a pre-declared outcome. This week Paper 2 becomes a proper trial. Three arms (mechanistic, pure ML, hybrid), four "doses" of data (5, 10, 20, 50 batches), five seeds each so luck cannot fake a result, conformal intervals so every number carries its honest uncertainty, and a stress test on fa…
THE NEXT BLOCK
Saturday sandbox · after Notin et al. (2023), "ProteinGym: large-scale benchmarks for protein fitness prediction and desi…
Andrew White, Deep Learning for Molecules and Materials — dmol.pub, chapter on "Deep learning on sequences" (with Colab buttons)
In: LABLOOP-W17 Notebook
By Sunday you should be able to say: “I can show the learning curve and say, with an interval, below how many batches the hybrid model is the better bet.”
MOMENTUM
2026-09-29 18:29 Finished: SciPy docs, scipy.integrate.solve_ivp2026-09-29 17:44 Finished: LearnChemE (CU Boulder) · "Monod Cell Growth Example (Bio)"2026-09-28 22:11 Finished: Crash Course Biology #3 · "Biological Molecules2026-09-28 21:50 Finished: OpenStax Biology 2e2026-09-25 11:16 Finished: OpenStax Biology 2e