Carbon efficient quantum AI: an empirical study of ansätz design trade-offs in QNN and QLSTM models
Sarvapriya Tripathi, Himanshu Upadhyay, Jayesh Soni · 2025
Read Carbon efficient quantum AI: an empirical study of ansätz design trade-offs in QNN and QLSTM models by Sarvapriya Tripathi, Himanshu Upadhyay, Jayesh Soni (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12749877.txt.
Description
Sarvapriya Tripathi, Himanshu Upadhyay, and Jayesh Soni weigh the carbon cost of quantum AI in a 2025 study. Green AI argues that model building should count its emissions. Quantum machine learning promises a leaner alternative, yet its real trade offs are unmeasured. The pair of model types tested were a quantum neural network and a quantum memory network, aimed at spotting intrusions in device data.
Ten circuit layouts, called ansätze, were compared on accuracy, complexity, training time, and energy. Simpler layouts matched the fancy ones on accuracy in the neural network case. If small quantum circuits do the job, their energy bill shrinks too. The study gives quantum designers an emissions yardstick.
Catalog record
| CREATOR | Sarvapriya Tripathi, Himanshu Upadhyay, Jayesh Soni |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 79 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |