Invention Grant
- Patent Title: Decision tree interface for neural networks
-
Application No.: US16860218Application Date: 2020-04-28
-
Publication No.: US11977990B2Publication Date: 2024-05-07
- Inventor: Zhong Fang Yuan , De Shuo Kong , Yun He Gao , Tong Liu , Peng Yun Sun , Ya Dong Li
- 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
- Agent Jeffrey M. Ingalls
- Main IPC: G06F21/00
- IPC: G06F21/00 ; G06F16/901 ; G06F18/243 ; G06N3/044 ; G06N3/063 ; G06N3/084 ; G06N5/045

Abstract:
A first set of features associated with a neural network are parameterized. A decision tree is generated from the first set of features. One or more adjustments for the neural network are received at the decision tree. A second set of features associated with the adjustments at the decision tree are parameterized. The parameterized first and second set of features are combined into a plurality of parameters. From the plurality, an adjusted neural network is generated.
Public/Granted literature
- US20210334632A1 DECISION TREE INTERFACE FOR NEURAL NETWORKS Public/Granted day:2021-10-28
Information query