@sepdek's

Geometry Meets Attention: Understanding SVDA from the Ground Up Based on our newly (2025) published IEEE Access paper: Geometry Meets Attention: Interpretable Transformers via SVD Inspiration Self-attention is the engine behind modern Transformers, but standard dot-product attention is a black box. Why does a model attend to certain tokens? Can we understand what dimensions matter […]

Recognising the value of light in life, humans throughout history devised ways of capturing the images created by light, while, at the same time, wondering and exploring the very nature of this magical element, sometimes using science, sometimes using logic and philosophy, and sometimes relying on feeling and superstition. What is certain is that light […]

Definition Typically, three Pythagorean means are defined and constitute the classical means used in various scientific fields; they are the arithmetic mean, the geometric mean, and the harmonic mean. Pythagoreans are reported to have first studied these means, along with later generations of Greek mathematicians, and this is why the means got the name ‘Pythagorean’. […]

A Brief History of Colour Theory tells the story of almost two and a half millennia, written by protagonists of a variety of characters. In the era of philosophy, colour science was founded upon logic, experience and philosophical worldviews. During the middle ages, the theory shifted towards experimental verification, although still strongly influenced by personal […]

I would never think of posting about something that trivial (at least it should be) as a guide to erase everything from an online calendar! The case here is about the Microsoft office 365 outlook calendar and how to wipe it clean for a fresh start. I have done an extensive search online on how […]

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 […]

Analysis of (time-series) data being collected in (near) realtime often provides insight for a process underway. As the current situation with COVID-19 is still critical lots of data are being collected, curated and streamed throughout the world, and researchers strive to get the most out of them to identify patterns and, maybe, make predictions. In […]

I was recently editing the second edition of my book on 3D digitisation using LaTeX and stumbled on an unexpected obstacle. The book consists of a number of chapters thus it is more convenient to edit them separately. In addition, I wanted to have bibliography at the end of each chapter, so that each chapter […]

The official Dropbox client application, at least to date, supports one and only one user account per personal computer user. This means that if a user has multiple accounts there is no official way to synchronise all Dropbox accounts under one personal computing device user account. Nevertheless, it is fairly easy and simple to activate […]

Clustering is an important category of machine learning methods and a main form of unsupervised learning. Clustering is essentially distinctive and substantially different from the other dominant form of machine learning, classification, in that it does not rely on training (supervised learning). In principle, clustering represents any method that tries to identify and distinguish groups […]

Of the most basic forms of a machine learning system based on neural networks is the one in which training is accomplished using back error propagation, or simply back-propagation. Back-propagation is a technique, like many others, that targets the minimisation of a cost function during a learning process by following the descending gradient of the […]

Machine learning is a research domain that is becoming the holy grail of data science towards the modelling and solution of science and engineering problems. I have already witnessed researchers proposing solutions to problems out of their area of expertise using machine learning methods, basing their approach on the success of modern machine learning algorithm […]