Invention Grant
- Patent Title: System and method for teaching compositionality to convolutional neural networks
-
Application No.: US16221104Application Date: 2018-12-14
-
Publication No.: US11216727B2Publication Date: 2022-01-04
- Inventor: Austin Charles Stone , Huayan Wang , D. Scott Phoenix , Dileep George
- Applicant: Vicarious FPC, Inc.
- Applicant Address: US CA Union City
- Assignee: Vicarious FPC, Inc.
- Current Assignee: Vicarious FPC, Inc.
- Current Assignee Address: US CA Union City
- Agent Jeffrey Schox; Diana Lin
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04 ; G10L15/16 ; G06K9/62 ; G06K9/46

Abstract:
A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.
Public/Granted literature
- US20190122112A1 SYSTEM AND METHOD FOR TEACHING COMPOSITIONALITY TO CONVOLUTIONAL NEURAL NETWORKS Public/Granted day:2019-04-25
Information query