Effiziente Decodierung von Ausgangssequenzen unter Verwendung von Gemeinsamer Parameternutzung

Details

Veröffentlichungs-Nr.

EP4722978

Anmeldetag

1. Oktober 2025

Veröffentlichung

8. April 2026

Rechtsraum

EP

IPC

G06N3/045(SCHUSTER TAL et al.)KUDO ET AL., ARXIV:1808.06226

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing a machine learning task. One of the methods includes generating an output sequence by, at each of a plurality of output time steps: generating a current input sequence from at least the tokens at output time steps that precede the output time step in the output sequence; generating a respective embedding for each input in the current input sequence; and processing the respective embeddings for the inputs in the current input sequence through one or more layer blocks in the sequence of layer blocks until a termination criterion is satisfied.

Anmelder

Firma

GDM Holding LLC

Land

🇺🇸 USA

Fachgebiete