Invention Grant
- Patent Title: System, method and apparatus for training neural networks using multiple datasets
-
Application No.: US16054358Application Date: 2018-08-03
-
Publication No.: US11640533B2Publication Date: 2023-05-02
- Inventor: Paul Nicholas Whatmough , Matthew Mattina , Jesse Garrett Beu
- Applicant: Arm Limited
- Applicant Address: GB Cambridge
- Assignee: Arm Limited
- Current Assignee: Arm Limited
- Current Assignee Address: GB Cambridge
- Agency: Leveque Intellectual Property Law, P.C.
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N20/00 ; G06N3/04 ; G06N3/082
Abstract:
A system, an apparatus and methods for utilizing software and hardware portions of a neural network to fix, or hardwire, certain portions, while modifying other portions are provided. A first set of weights for layers of the first neural network are established, and selected weights are modified to generate a second set of weights, based on a second dataset. The second set of weights is then used to train a second neural network.
Public/Granted literature
- US20200042877A1 SYSTEM, METHOD AND APPARATUS FOR NEURAL NETWORKS Public/Granted day:2020-02-06
Information query
