Machine Learning Models for a Novel Optical Memory Approach
Tal Raviv, Zeev Kalyuzhner, Zeev Zalevsky · 2024
Read Machine Learning Models for a Novel Optical Memory Approach by Tal Raviv, Zeev Kalyuzhner, Zeev Zalevsky (2024) 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-11683637.txt.
Description
Tal Raviv, Zeev Kalyuzhner, and Zeev Zalevsky apply machine learning to a light-based memory in this 2024 paper. Their memory stores data in how gold nanoparticles scatter light, giving a lasting optical record. Reading it means sorting the scatter patterns into the right classes, a job where learning methods can sharpen the result.
The team used a random forest method to classify the scattered images and a mapping method to view their structure. The classifier sorted the patterns into nine classes with accuracy and average quality scores of about zero point eight one. The authors frame the work as one step toward all-optical data handling for data centers, where speed and bandwidth demands keep climbing. Memory that holds its state without power is a key missing piece in that vision.
Catalog record
| CREATOR | Tal Raviv, Zeev Kalyuzhner, Zeev Zalevsky |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 18 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |