Teaching myself how to build a Spiking Graph Neural Network in Zig, to run on my Brainchip Akida AKD1500 neuromorphic accelerators (and Efinix Titanium Ti60 FPGAs).
Good times, but lots of foundational math I hadn't previously been exposed to.
Some reading material if anyone else is interested in that:
While it's true that 2.0 makes recursive CTEs much more performant, don't forget that there's a badass DuckDB extension for graph data already. Here's a 2025 article about how elegantly that can handle what is otherwise quite a challenging class of query for your typical RDBMS: https://duckdb.org/2025/10/22/duckdb-graph-queries-duckpgq
This is perhaps the most "metal concept album"-ready Nature article title I have seen. My Nature+ subscription is paying the bills this month, for sure.
I am sure this is a nice article, but I'm always surprised when something with a hard paywall makes it this high up on HN. Does everybody but me have a Financial Times subscription?
Good times, but lots of foundational math I hadn't previously been exposed to.
Some reading material if anyone else is interested in that:
Spiking Graph Convolutional Networks (2022): https://doi.org/10.24963/ijcai.2022/338
A Tutorial on Spectral Clustering (2007): https://doi.org/10.1007/s11222-007-9033-z
Semi-Supervised Clustering with Graph Convolutional Networks (2017): https://arxiv.org/abs/1609.02907
Spectral and Algebraic Graph Theory (2025, draft book): http://cs-www.cs.yale.edu/homes/spielman/sagt/sagt.pdf
reply