Invention Grant
- Patent Title: Neural network connection reduction
-
Application No.: US15408407Application Date: 2017-01-17
-
Publication No.: US11195094B2Publication Date: 2021-12-07
- Inventor: Michael Lee
- Applicant: FUJITSU LIMITED
- Applicant Address: JP Kawasaki
- Assignee: FUJITSU LIMITED
- Current Assignee: FUJITSU LIMITED
- Current Assignee Address: JP Kawasaki
- Agency: Maschoff Brennan
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04

Abstract:
A method of updating a neural network may be provided. A method may include selecting a number of neurons for a layer for a neural network such that the number of neurons in the layer is less than at least one of a number of neurons in a first layer of the neural network and a number of neurons in a second, adjacent layer of the neural network. The method may further include and at least one of inserting the layer between the first layer and the second layer of the neural network and replacing one of the first layer and the second layer with the layer to reduce a number of connections in the neural network.
Public/Granted literature
- US20180204115A1 NEURAL NETWORK CONNECTION REDUCTION Public/Granted day:2018-07-19
Information query