What is it about?
We used a simple neural network, along with some novel tokenisation of character strings, to automatically label building equipment according to their names. Lightweight, fast to train, limited dataset, yet achieved a respectable 91% labelling accuracy.
Featured Image
Photo by Jonah Pettrich on Unsplash
Why is it important?
Because you don't need "Quantum Blockchain Large Language Models with Distributed Graph Neural Networks on Homomorphic Encrypted Cloud-based Neuro-morphic Cognitive Ambient Computing supported by Room Temperature Quantum Super-Entangled Organic Super Conducting IoT platform" to solve simple problems. KISS (keep it small and simple) :D
Perspectives
I think the work is good, if I do say so myself.
Mahathir Almashor
CSIRO
Read the Original
This page is a summary of: What's The Point: AutoEncoding Building Point Names, November 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3600100.3623748.
You can read the full text:
Contributors
The following have contributed to this page
