Getting started with deep learning on graphs
This post introduces deep learning on graphs by mapping its central concept - message passing - to minimal usage patterns of PyTorch Geometric’s foundation-laying MessagePassing class. Exploring those patterns, we gain some basic, very concrete insights into how graph DL works.
A book I’d say everyone should read if such were a kind of thing I’d say
Much as we humans like to believe, consciousness is not a neocortex thing, a matter of analysis and meta-analysis. Instead – says Mark Solms, in his 2021 The Hidden Spring: A Journey to the Source of Consciousness – instead, consciousness is all about feeling. A claim that, if we take it seriously (and I don’t see why we shouldn’t) has far-ranging consequences.
AI ethics is not an optimization problem
Often, AI researchers and engineers think of themselves as neutral and “objective”, operating in a framework of strict formalization. Fairness and absence of bias, however, are social constructs; there is no objectivity, no LaTeX-typesettable remedies, no algorithmic way out. AI models are developed based on a history and deployed in a context. In AI as in data science, the very absence of action can be of political significance.
The hard problem of privacy
We live in a world of ever-diminishing privacy and ever-increasing surveillance - and this is a statement not just about openly-authoritarian regimes. Yet, we seem not to care that much, at least not until, for whatever reasons, we are personally affected by some negative consequence. This post wants to help increase awareness, casting a spotlight on recent history and also, letting words speak for themselves: Because nothing, to me, is less revealing than the “visions” that underly the actions.