GENERATING OUTPUT EXAMPLES USING RECURRENT NEURAL NETWORKS CONDITIONED ON BIT VALUES

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output examples using neural networks. One of the methods includes, at each generation time step, processing a first recurrent input comprising an N-bit output value at the preceding genera...

Full description

Saved in:
Bibliographic Details
Main Authors KALCHBRENNER, Nal Emmerich, ELSEN, Erich Konrad, SIMONYAN, Karen
Format Patent
LanguageEnglish
French
German
Published 26.08.2020
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output examples using neural networks. One of the methods includes, at each generation time step, processing a first recurrent input comprising an N-bit output value at the preceding generation time step in the sequence using a recurrent neural network and in accordance with a hidden state to generate a first score distribution; selecting, using the first score distribution, values for the first half of the N bits; processing a second recurrent input comprising (i) the N-bit output value at the preceding generation time step and (ii) the values for the first half of the N bits using the recurrent neural network and in accordance with the same hidden state to generate a second score distribution; and selecting, using the second score distribution, values for the second half of the N bits of the output value.
Bibliography:Application Number: EP20190704794