Subject · 21 posts
A bank rents the biggest MoE around, salary day brings a thousand customers, and the team learns what to prune, why Bangla breaks, and when to teach a student.
Mixture of Experts03
A gentle, playful look at k-nearest neighbours, the lazy way a computer labels something new by asking the dots closest to it.
A gentle beginner guide to activation functions, the little curves that let neural networks learn curvy and complicated patterns.
Slide a line to sort blue apples from pink oranges, and learn how a classifier sorts new things the way spam filters do.
A gentle beginner guide to k-means clustering, where a computer sorts dots into groups on its own, using a tiny web game you can try.
A gentle beginner guide to overfitting, where sliding a line from plain to wiggly shows why the middle fit works best on new data.
Learn how a single pretend brain cell weighs its inputs and lights up, the simplest idea behind every neural network.
A gentle beginner guide to gradient descent, the roll-the-ball-downhill trick that quietly trains almost every kind of artificial intelligence.
A plain tour of every tiny game in the arcade: what you do in each one, and the big idea it sneaks in, from fractions to how a neural network learns.
Press Train and watch a small network of cells learn a pattern one cell cannot, a gentle first look at neural networks and backpropagation.
A funnel from every catalogued natural product down to twenty compounds worth testing, and why the split and the base rate matter more than the model.
Machine Learning for Biology05
Random UniProt negatives quietly turn peptide prediction into short versus long. Here is what an honest benchmark costs, and why it is worth paying.
Machine Learning for Biology04
A 650-million-parameter protein language model, what its embeddings really encode, and why twenty lines of letter counting still beat it on 13-residue peptides.
Machine Learning for Biology03
AAC, DPC, DDE, CKSAAP, CTD, PAAC and QSO: every way I know to turn a peptide into a fixed-length vector, and what each one throws away.
Machine Learning for Biology02
What a peptide actually is, why order and side chains carry the information, and why 13 residues is a different modelling problem from 300.
Machine Learning for Biology01
Why a mixture-of-experts layer runs at the speed of its busiest expert, how to measure it, and when predictive prefetching actually helps.
Mixture of Experts02
A laptop-sized toolkit for context-aware lexical substitution, and an honest look at what tiny models actually score on it.
How sparse mixture-of-experts really works: per-token routing, top-k gating, load balancing, and the memory bill you pay for the compute you save.
Mixture of Experts01
What a deep-learning framework actually does for you, how a decision tree picks its questions, and which of the three to reach for on real data.
AI Foundations02
Four algorithms in forty lines each, with no library. k-nearest neighbours, linear and logistic regression, k-means, and a decision tree, plus what each one assumes.
Problem Solving From Zero20
What homomorphic encryption really does, which scheme to pick, what a ciphertext costs in bytes and depth, and where it still loses to a trusted enclave.