Jump to content

18972483. GENERATING CODED DATA REPRESENTATIONS USING NEURAL NETWORKS AND VECTOR QUANTIZERS (Google LLC)

From WikiPatents

GENERATING CODED DATA REPRESENTATIONS USING NEURAL NETWORKS AND VECTOR QUANTIZERS

Organization Name

Google LLC

Inventor(s)

Neil Zeghidour of Paris FR

Marco Tagliasacchi of Ruvigliana CH

Dominik Roblek of Meilen CH

GENERATING CODED DATA REPRESENTATIONS USING NEURAL NETWORKS AND VECTOR QUANTIZERS

This abstract first appeared for US patent application 18972483 titled 'GENERATING CODED DATA REPRESENTATIONS USING NEURAL NETWORKS AND VECTOR QUANTIZERS

Original Abstract Submitted

Methods, systems and apparatus, including computer programs encoded on computer storage media. According to one aspect, there is provided a method comprising: receiving a new input; processing the new input using an encoder neural network to generate a feature vector representing the new input; and generating a coded representation of the feature vector using a sequence of vector quantizers that are each associated with a respective codebook of code vectors, wherein the coded representation of the feature vector identifies a plurality of code vectors, including a respective code vector from the codebook of each vector quantizer, that define a quantized representation of the feature vector.

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