Invention Grant
- Patent Title: Method for generating neural network and electronic device
-
Application No.: US16666344Application Date: 2019-10-28
-
Publication No.: US11195098B2Publication Date: 2021-12-07
- Inventor: Yukang Chen , Qian Zhang , Chang Huang
- Applicant: Beijing Horizon Robotics Technology Research and Development Co., Ltd.
- Applicant Address: CN Beijing
- Assignee: Beijing Horizon Robotics Technology Research and Development Co., Ltd.
- Current Assignee: Beijing Horizon Robotics Technology Research and Development Co., Ltd.
- Current Assignee Address: CN Beijing
- Agency: Westbridge IP LLC
- Priority: CN201811269254.8 20181029
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06K9/62 ; G06N20/20 ; G06N3/04

Abstract:
Disclosed are a method for generating a neural network, an apparatus thereof, and an electronic device. The method includes: obtaining an optimal neural network and a worst neural network from a neural network framework by using an evolutionary algorithm; obtaining an optimized neural network from the optimal neural network by using a reinforcement learning algorithm; updating the neural network framework by adding the optimized neural network into the neural network framework and deleting the worst neural network from the neural network framework; and determining an ultimately generated neural network from the updated neural network framework. In this way, a neural network is optimized and updated from a neural network framework by combining the evolutionary algorithm and the reinforcement learning algorithm, thereby automatically generating a neural network structure rapidly and stably.
Information query