Invention Grant
- Patent Title: High-capacity machine learning system
-
Application No.: US14851336Application Date: 2015-09-11
-
Publication No.: US10229357B2Publication Date: 2019-03-12
- Inventor: Ou Jin , Stuart Michael Bowers , Dmytro Dzhulgakov
- Applicant: Facebook, Inc.
- Applicant Address: US CA Menlo Park
- Assignee: Facebook, Inc.
- Current Assignee: Facebook, Inc.
- Current Assignee Address: US CA Menlo Park
- Agency: Fenwick & West LLP
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N99/00

Abstract:
The present disclosure is directed to a high-capacity training and prediction machine learning platform that can support high-capacity parameter models (e.g., with 10 billion weights). The platform implements a generic feature transformation layer for joint updating and a distributed training framework utilizing shard servers to increase training speed for the high-capacity model size. The models generated by the platform can be utilized in conjunction with existing dense baseline models to predict compatibilities between different groupings of objects (e.g., a group of two objects, three objects, etc.).
Public/Granted literature
- US20170076198A1 HIGH-CAPACITY MACHINE LEARNING SYSTEM Public/Granted day:2017-03-16
Information query