Invention Grant
- Patent Title: Constructing and processing computational graphs for dynamically structured machine learning models
-
Application No.: US15344160Application Date: 2016-11-04
-
Publication No.: US10776714B2Publication Date: 2020-09-15
- Inventor: Marcello Mathias Herreshoff
- Applicant: Google Inc.
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06N20/00
- IPC: G06N20/00 ; G06N5/02 ; G06F8/41 ; G06F40/20

Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for constructing and processing computational graphs that represent dynamically structured machine learning models are disclosed. An example system receives data identifying a plurality of operations that can be performed on input data for processing by a dynamically structured machine learning model. The system also receives a plurality of labels corresponding to arguments for the plurality of operations. A directed computational graph representing a comprehensive layer of the dynamically structured machine learning model is generated from the identified operations and labels. An example system then receives an input for processing by the machine learning model and specifies data flow through the directed computational graph.
Public/Granted literature
- US20180129967A1 CONSTRUCTING AND PROCESSING COMPUTATIONAL GRAPHS FOR DYNAMICALLY STRUCTURED MACHINE LEARNING MODELS Public/Granted day:2018-05-10
Information query