Gradient descent on a quadratic you can solve exactly
Solve gradient descent on a scalar quadratic exactly, identify the stable learning-rate interval, and distinguish convergence from oscillation.
Foundation
The journal / Ideas in progress
Engineering & everyday learningNotes from
the work.
Software, systems, and the things I’m learning along the way. From first principles to AI in production.
Find something to readAll notes 15
A little theory. A lot of practice.
Build a data inventory before a handbook assistant
Map source authority, permitted uses, audience and derived copies in a fictional handbook assistant, then design a concrete document-withdrawal exercise.
Foundation
Split by the person when the person is the prediction boundary
Compare lookup errors under recording and speaker splits, then construct connected blocks that keep both speakers and devices separate.
Foundation
Balancing full-stack breadth with depth
Balance full-stack breadth with depth by investigating an inventory update bug and defining observable learning goals.
Foundation
Check a gradient with finite differences before trusting training
Derive central-difference error, expose floating-point cancellation and a hidden gradient bug, and test the limits of directional checks.
Foundation
Likelihood is a function of the parameter
Derive a Bernoulli likelihood, compare sample-size effects and serial dependence, and reproduce why equal success counts need not mean equal sequence probabilities.
Foundation
Write a learning roadmap with stopping rules
Give a developer learning roadmap stopping rules, useful evidence and a deferred list that keeps curiosity from expanding every task.
Foundation
Expected loss and variance from a tiny discrete distribution
Calculate expected loss, variance and the distribution of a two-case average, then test how copied observations and rare large failures change the evaluation.
Foundation
Carry accessibility questions from web to desktop
Trace a modal dialog through focus, keyboard and accessibility-tree checks in Chromium, then define the remaining Electron and screen-reader checks.
Foundation
Ask useful questions in your first backend review
Ask precise backend review questions about identity, partial updates and external effects, even while learning the codebase.
Foundation
Choose the next skill by its dependencies
Choose the next skill from the dependencies of a receipt organizer, with clear questions and evidence for each boundary.
Foundation
Read residuals before adding another model
Fit a tiny linear model, recognize curvature in its residuals, and separate misspecified mean structure from changes in error spread.
Foundation