Broadband encoding and high-speed probabilistic bit generation with integrated microwave neurons
Bala Govind, Pablo Raigoza, Alyssa Apsel · 2026
Read Broadband encoding and high-speed probabilistic bit generation with integrated microwave neurons by Bala Govind, Pablo Raigoza, Alyssa Apsel (2026) 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/PMC13527087.txt.
Description
Govind, Raigoza, and Apsel reported in 2026 a microwave neural network that processes radio signals directly, without first converting them to digital form. Digitising first adds delay and power cost and caps speed at the digital clock rate. Their chip, built in standard CMOS technology, lets incoming data itself reshape links between frequency modes across several gigahertz of bandwidth, spreading each data token across a wide spectrum.
Govind shows that spreading the tokens this way makes links between successive tokens easier for light digital stages to spot, speeding final decisions. The network runs on milliwatt-scale power. When fed fast bitstreams such as pixel data, it also produced probabilistic bits, outputs that flip with a bias set by the input pattern. This dithering keeps detail in compressed data, and the authors suggest richer satellite imaging at a fraction of the usual data rate.
Catalog record
| CREATOR | Bala Govind, Pablo Raigoza, Alyssa Apsel |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |