Invention Grant
- Patent Title: Scalable extensible neural network system and methods
-
Application No.: US16352669Application Date: 2019-03-13
-
Publication No.: US11488011B2Publication Date: 2022-11-01
- Inventor: Stuart H. Rubin
- Applicant: SPAWAR Systems Center Pacific
- Applicant Address: US CA San Diego
- Assignee: SPAWAR Systems Center Pacific
- Current Assignee: SPAWAR Systems Center Pacific
- Current Assignee Address: US CA San Diego
- Agency: Naval Information Warfare Center, Pacific
- Agent Kyle Eppele; Evan Hastings
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06F1/16 ; A61B5/00 ; A61B5/242

Abstract:
A neural network system, involving a neural network, the neural network configured to: map sensor output to a Level 1 input; learn to fuse the time slices for one class, learning comprising taking and feeding a random assignment of inputs from each time slice into a threshold function for another two-dimensional array; learn to reject class bias for completing network training; use cycles for class recognition, and fuse segments for intelligent information dominance and a magnetic headwear apparatus operably coupled with the neural network.
Public/Granted literature
- US20200293879A1 Scalable Extensible Neural Network System and Methods Public/Granted day:2020-09-17
Information query