Invention Grant
- Patent Title: Discrete feature representation with class priority
-
Application No.: US16290250Application Date: 2019-03-01
-
Publication No.: US11244227B2Publication Date: 2022-02-08
- Inventor: Masataro Asai
- Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Applicant Address: US NY Armonk
- Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Current Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
- Current Assignee Address: US NY Armonk
- Agency: Tutunjian & Bitetto, P.C.
- Agent Randall Bluestone
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06K9/62 ; G06N20/00 ; G06N3/04

Abstract:
A discrete neural network is trained by training a neural network having an output layer so as to output discrete values. The output layer includes a plurality of nodes. Each node corresponding to one of a plurality of classes. The training includes activating the nodes by priority according to the corresponding class.
Public/Granted literature
- US20200279164A1 DISCRETE FEATURE REPRESENTATION WITH CLASS PRIORITY Public/Granted day:2020-09-03
Information query