DataMUX: Data Multiplexing for Neural Networks

In this paper, we introduce data multiplexing (DataMUX), a technique that enables deep neural networks to process multiple inputs simultaneously using a single compact representation. DataMUX demonstrates that neural networks are capable of generating accurate predictions over mixtures of inputs, re...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-11
Hauptverfasser:	Murahari, Vishvak, Jimenez, Carlos E, Yang, Runzhe, Narasimhan, Karthik
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Demultiplexing Image classification Linear transformations Multiplexing Neural networks Object recognition Representations Transformers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!