Skip to content
Descubridor Institucional UMAR
Inicio
Búsqueda avanzada
Explorar
Inicio
Búsqueda avanzada
Explorar
Login
Language
English
Deutsch
Español
Français
Italiano
All Fields
Title
Author
Subject
Call Number
ISBN/ISSN
Tag
Find
Advanced
Lossy Loops: Shannon's DPI and Information Decay in Generative Model Training
Lossy Loops: Shannon's DPI and Information Decay in Generative Model Training
Fuente:
Zenodo
Saved in:
Bibliographic Details
Main Author:
Straňák, Pavel
Format:
Recurso digital
Language:
English
Published:
Zenodo
2025
Subjects:
Model collapse, Information theory, Data Processing Inequality, Generative AI, Synthetic data, Mutual information, AI limitations
Online Access:
Acceder al recurso
Tags:
Add Tag
No Tags, Be the first to tag this record!
Cite this
Text this
Email this
Print
Export Record
Export to RefWorks
Export to EndNoteWeb
Export to EndNote
Save to List
Permanent link
Holdings
Description
Comments
Similar Items
Staff View
Internet
https://doi.org/10.5281/zenodo.16481493
Similar Items
Global AI in Synthetic Biology Market 2025 To 2034
by: Sirsat, Nitin
Published: (2025)
Toward A Cooperative AI Ecosystem
by: van der Erve, Marcus
Published: (2024)
Non-Conditional Anatomically-Accurate 2D Synthetic Mask Generation
by: Azevedo, Diogo Amaral, et al.
Published: (2025)
The Informational Basis of Social Choice under Model Uncertainty: Transparency, Robustness, and a Social-Choice Nyquist Limit
by: Fathi, Kevin
Published: (2026)
Epistemic Fabric: A Formal Topological Solution to the Goodhart Collapse
by: Yalcinkaya, Erkan
Published: (2026)