Invention Grant
- Patent Title: Small-world nets for fast neural network training and execution
-
Application No.: US16661226Application Date: 2019-10-23
-
Publication No.: US11625614B2Publication Date: 2023-04-11
- Inventor: Mojan Javaheripi , Farinaz Koushanfar , Bita Darvish Rouhani
- Applicant: The Regents of the University of California
- Applicant Address: US CA Oakland
- Assignee: The Regents of the University of California
- Current Assignee: The Regents of the University of California
- Current Assignee Address: US CA Oakland
- Agency: Mintz Levin Cohn Ferris Glovsky and Popeo, P.C.
- Main IPC: G06N3/10
- IPC: G06N3/10 ; G06N3/04 ; G06F16/901
Abstract:
A method, a system, and a computer program product for fast training and/or execution of neural networks. A description of a neural network architecture is received. Based on the received description, a graph representation of the neural network architecture is generated. The graph representation includes one or more nodes connected by one or more connections. At least one connection is modified. Based on the generated graph representation, a new graph representation is generated using the modified at least one connection. The new graph representation has a small-world property. The new graph representation is transformed into a new neural network architecture.
Information query
