python

sepdek September 24, 2026

My July 2025 introduction to SVDA focused on understanding attention. Here I want to explore a practical question: once we can inspect a model’s internal directions, how do we decide which ones to keep—and how do we check that an implementation change does what we intended? Research context Our paper, Prescriptive SVD-Inspired Attention via Spectral […]

sepdek May 7, 2026

Two training runs can have identical current parameters and still take different next steps. That is not mysterious if their optimizer states differ. It becomes easy to overlook when we inspect only the weights or the current prediction. The question worth asking is therefore precise: what state are we observing, what history are we controlling, […]

sepdek December 10, 2025

Suppose a collection contains a small set of confirmed matches and thousands of items nobody has checked. Treating every unchecked item as a non-match gives us a convenient training table—but some of its labels will be invented. This is the starting point of positive–unlabelled learning. We know that certain examples are positive. For the others, […]

sepdek March 29, 2020

In a recent post (Analysis of live COVID-19 data – a MATLAB/Octave approach) I described how it is possible to analyse live COVID-19 data from reliable online data sources and create intuitive graphical representations. Apparently, this task is also simple when using Python programming language. To this end, a Colab Python notebook was created to […]