公开(公告)号：US20250124356A1

公开(公告)日：2025-04-17

申请号：US19000568

申请日：2024-12-23

Applicant: Apple Inc.

Inventor： Thomas FOGAL ,  Adam NEMET ,  Gerolf F. HOFLEHNER

IPC: G06N20/00 ,  G06F8/41 ,  G06F16/245

Abstract: The subject technology provides a framework for executable machine learning models that are executable in a zero-runtime operating environment. This allows the machine learning models to be deployed in limited memory environments such as embedded domains. A machine learning compiler is provided to generate the executable machine learning models.

公开(公告)号：US20210398015A1

公开(公告)日：2021-12-23

申请号：US17094772

申请日：2020-11-10

Applicant: Apple Inc.

Inventor： Thomas FOGAL ,  Adam NEMET ,  Gerolf F. HOFLEHNER

IPC: G06N20/00 ,  G06F8/41

Abstract: The subject technology provides a framework for executable machine learning models that are executable in a zero-runtime operating environment. This allows the machine learning models to be deployed in limited memory environments such as embedded domains. A machine learning compiler is provided to generate the executable machine learning models.