Invention Grant
- Patent Title: Crossbar arrays for computations in memory-augmented neural networks
-
Application No.: US16862441Application Date: 2020-04-29
-
Publication No.: US11604976B2Publication Date: 2023-03-14
- Inventor: Thomas Bohnstingl , Angeliki Pantazi , Stanislaw Andrzej Wozniak , Evangelos Stavros Eleftheriou
- Applicant: International Business Machines Corporation
- Applicant Address: US NY Armonk
- Assignee: International Business Machines Corporation
- Current Assignee: International Business Machines Corporation
- Current Assignee Address: US NY Armonk
- Agent Edward J. Wixted, III
- Main IPC: G06N3/063
- IPC: G06N3/063 ; G06N3/04

Abstract:
In a hardware-implemented approach for operating a neural network system, a neural network system is provided comprising a controller, a memory, and an interface connecting the controller to the memory, where the controller comprises a processing unit configured to execute a neural network and the memory comprises a neuromorphic memory device with a crossbar array structure that includes input lines and output lines interconnected at junctions via electronic devices. The electronic devices of the neuromorphic memory device are programmed to incrementally change states by coupling write signals into the input lines based on: write instructions received from the controller and write vectors generated by the interface. Data is retrieved from the neuromorphic memory device, according to a multiply-accumulate operation, by coupling read signals into one or more of the input lines of the neuromorphic memory device based on: read instructions from the controller and read vectors generated by the interface.
Public/Granted literature
- US20210342672A1 CROSSBAR ARRAYS FOR COMPUTATIONS IN MEMORY-AUGMENTED NEURAL NETWORKS Public/Granted day:2021-11-04
Information query