Invention Grant
- Patent Title: Computer architecture for and-or neural networks
-
Application No.: US16170656Application Date: 2018-10-25
-
Publication No.: US11037027B2Publication Date: 2021-06-15
- Inventor: Philip A. Sallee
- Applicant: Raytheon Company
- Applicant Address: US MA Waltham
- Assignee: Raytheon Company
- Current Assignee: Raytheon Company
- Current Assignee Address: US MA Waltham
- Agency: Schwegman Lundberg & Woessner, P.A.
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06N3/08 ; G06N3/04

Abstract:
A computer architecture for an and-or neural network is disclosed. A computing machine accesses an input vector. The input vector comprises a numeric representation of an input to a neural network. The computing machine provides the input vector to the neural network comprising a plurality of ordered layers. The plurality of ordered layers are alternating AND-layers and OR-layers. Each of the plurality of ordered layers receives input from a preceding layer and/or provides output to a next layer. The computing machine generates an output of the neural network based on an output of a last one of the plurality of ordered layers in the neural network.
Information query