Invention Grant
- Patent Title: Hardware accelerators for calculating node values of neural networks
-
Application No.: US15570951Application Date: 2016-03-11
-
Publication No.: US10332592B2Publication Date: 2019-06-25
- Inventor: John Paul Strachan , Brent Buchanan , Le Zheng
- Applicant: Hewlett Packard Enterprise Development LP
- Applicant Address: US TX Houston
- Assignee: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP
- Current Assignee: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP
- Current Assignee Address: US TX Houston
- Agency: Hewlett Packard Enterprise Patent Department
- International Application: PCT/US2016/022052 WO 20160311
- International Announcement: WO2017/155544 WO 20170914
- Main IPC: G11C11/54
- IPC: G11C11/54 ; G06F9/06 ; G06N3/063 ; G11C13/00 ; G11C7/10 ; G06N3/04

Abstract:
Examples herein relate to hardware accelerators for calculating node values of neural networks. An example hardware accelerator may include a crossbar array programmed to calculate node values of a neural network and a current comparator to compare an output current from the crossbar array to a threshold current according to an update rule to generate new node values. The crossbar array has a plurality of row lines, a plurality of column lines, and a memory cell coupled between each unique combination of one row line and one column line, where the memory cells are programmed according to a weight matrix. The plurality of row lines are to receive an input vector of node values, and the plurality of column lines are to deliver an output current to be compared with the threshold current.
Public/Granted literature
- US20180114569A1 HARDWARE ACCELERATORS FOR CALCULATING NODE VALUES OF NEURAL NETWORKS Public/Granted day:2018-04-26
Information query