Invention Grant
- Patent Title: Training of student neural network with switched teacher neural networks
-
Application No.: US16047287Application Date: 2018-07-27
-
Publication No.: US11610108B2Publication Date: 2023-03-21
- Inventor: Takashi Fukuda , Masayuki Suzuki , Osamu Ichikawa , Gakuto Kurata , Samuel Thomas , Bhuvana Ramabhadran
- 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 Randy Emilio Tejeda
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04
Abstract:
A student neural network may be trained by a computer-implemented method, including: selecting a teacher neural network among a plurality of teacher neural networks, inputting an input data to the selected teacher neural network to obtain a soft label output generated by the selected teacher neural network, and training a student neural network with at least the input data and the soft label output from the selected teacher neural network.
Public/Granted literature
- US20200034702A1 TRAINING OF STUDENT NEURAL NETWORK WITH SWITCHED TEACHER NEURAL NETWORKS Public/Granted day:2020-01-30
Information query
