Invention Grant
- Patent Title: Three-dimensional (3D) convolution with 3D batch normalization
-
Application No.: US15237575Application Date: 2016-08-15
-
Publication No.: US10282663B2Publication Date: 2019-05-07
- Inventor: Richard Socher , Caiming Xiong , Kai Sheng Tai
- Applicant: salesforce.com, inc.
- Applicant Address: US CA San Francisco
- Assignee: salesforce.com, inc.
- Current Assignee: salesforce.com, inc.
- Current Assignee Address: US CA San Francisco
- Agency: Haynes and Boone, LLP
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04 ; G06F17/50 ; G06K9/46 ; G06T7/00 ; G06K9/00 ; G06K9/62

Abstract:
The technology disclosed uses a 3D deep convolutional neural network architecture (DCNNA) equipped with so-called subnetwork modules which perform dimensionality reduction operations on 3D radiological volume before the 3D radiological volume is subjected to computationally expensive operations. Also, the subnetworks convolve 3D data at multiple scales by subjecting the 3D data to parallel processing by different 3D convolutional layer paths. Such multi-scale operations are computationally cheaper than the traditional CNNs that perform serial convolutions. In addition, performance of the subnetworks is further improved through 3D batch normalization (BN) that normalizes the 3D input fed to the subnetworks, which in turn increases learning rates of the 3D DCNNA. After several layers of 3D convolution and 3D sub-sampling with 3D across a series of subnetwork modules, a feature map with reduced vertical dimensionality is generated from the 3D radiological volume and fed into one or more fully connected layers.
Public/Granted literature
- US20170046616A1 THREE-DIMENSIONAL (3D) CONVOLUTION WITH 3D BATCH NORMALIZATION Public/Granted day:2017-02-16
Information query