MICROSOFT WORLDWIDE MEDIA AND ENTERTAINMENT STRATEGY DIRECTOR SIMON CROWNSHAW TALKS GEN AI

Crownshaw also digs deep into how Microsoft is building asset management architecture and the critical role metadata plays in effective large-language models (LLMs), maximizing the value of available data. Some of the video analysis could go through a temporal convolution-based long short-term memor...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Streaming Media Magazine 2024-09, Vol.21 (5), p.34-40
1. Verfasser: Krefetz, Nadine
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Crownshaw also digs deep into how Microsoft is building asset management architecture and the critical role metadata plays in effective large-language models (LLMs), maximizing the value of available data. Some of the video analysis could go through a temporal convolution-based long short-term memory (TCLSTM) network and others to understand that. The more efficient you can make it, the more you can reduce the compute power required. Because you're dealing with a lot of old assets that have grown organically over time, it needs to be synthesized in a way that the large language models can understand.
ISSN:1559-8039
1531-7315