Jump to content

18835613. MERGING ELEMENTS OF SEQUENCES DURING NEURAL NETWORK PROCESSING (Google LLC)

From WikiPatents


MERGING ELEMENTS OF SEQUENCES DURING NEURAL NETWORK PROCESSING

Organization Name

Google LLC

Inventor(s)

Cédric Benjamin Renggli of Uster CH

Carlos Riquelme Ruiz of Zurich CH

André Susano Pinto of Zürich CH

Basil Mustafa of Zurich CH

Joan Puigcerver I Perez of Zurich CH

Neil Matthew Tinmouth Houlsby of Zurich CH

MERGING ELEMENTS OF SEQUENCES DURING NEURAL NETWORK PROCESSING

This abstract first appeared for US patent application 18835613 titled 'MERGING ELEMENTS OF SEQUENCES DURING NEURAL NETWORK PROCESSING

Original Abstract Submitted

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more merger neural network blocks that each generate block output sequence that has fewer elements than the block input sequence that is processed by the merger neural network block.

(Ad) Transform your business with AI in minutes, not months

Custom AI strategy tailored to your specific industry needs
Step-by-step implementation with measurable ROI
5-minute setup that requires zero technical skills
Get your AI playbook

Trusted by 1,000+ companies worldwide

Cookies help us deliver our services. By using our services, you agree to our use of cookies.