Invention Grant
- Patent Title: Parallelizing neural networks during training
-
Application No.: US14030938Application Date: 2013-09-18
-
Publication No.: US09811775B2Publication Date: 2017-11-07
- Inventor: Alexander Krizhevsky , Ilya Sutskever , Geoffrey E. Hinton
- Applicant: Google Inc.
- Applicant Address: US CA Mountain View
- Assignee: Google Inc.
- Current Assignee: Google Inc.
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06F15/18
- IPC: G06F15/18 ; G06N3/04 ; G06K9/66 ; G06K9/62 ; G06T1/20 ; G06N3/063 ; G06K9/46

Abstract:
A parallel convolutional neural network is provided. The CNN is implemented by a plurality of convolutional neural networks each on a respective processing node. Each CNN has a plurality of layers. A subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. The remaining subset is not so interconnected.
Public/Granted literature
- US20140180989A1 SYSTEM AND METHOD FOR PARALLELIZING CONVOLUTIONAL NEURAL NETWORKS Public/Granted day:2014-06-26
Information query