18528935. ACCELERATION OF MODEL/WEIGHT PROGRAMMING IN MEMRISTOR CROSSBAR ARRAYS simplified abstract (HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP)

From WikiPatents
Revision as of 03:56, 16 April 2024 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

ACCELERATION OF MODEL/WEIGHT PROGRAMMING IN MEMRISTOR CROSSBAR ARRAYS

Organization Name

HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor(s)

Sai Rahul Chalamalasetti of Milpitas CA (US)

Paolo Faraboschi of Sant Cugat (ES)

Martin Foltin of Fort Collins CO (US)

Catherine Graves of Milpitas CA (US)

Dejan S. Milojicic of Palo Alto CA (US)

John Paul Strachan of San Carlos CA (US)

Sergey Serebryakov of Saint-Petersburg (RU)

ACCELERATION OF MODEL/WEIGHT PROGRAMMING IN MEMRISTOR CROSSBAR ARRAYS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18528935 titled 'ACCELERATION OF MODEL/WEIGHT PROGRAMMING IN MEMRISTOR CROSSBAR ARRAYS

Simplified Explanation

The abstract describes a patent application for a crossbar array system that includes memory elements, an analog-to-digital converter (ADC), a digital-to-analog converter (DAC), and a processor. The processor is responsible for determining changes in data values between input and output vector data from the crossbar array and writing these changes to the memory elements.

  • The patent application describes a crossbar array system with memory elements, an ADC, a DAC, and a processor.
  • The processor is tasked with analyzing input and output vector data from the crossbar array to identify changes in data values.
  • Once changes are detected, the processor writes these new data values to the memory elements of the crossbar array.

Potential Applications

This technology could be applied in various fields such as signal processing, image recognition, and machine learning.

Problems Solved

This technology helps in efficiently managing and updating data values within a crossbar array system, improving overall performance and accuracy.

Benefits

The system allows for real-time analysis and updating of data values, enhancing the efficiency and effectiveness of the crossbar array.

Potential Commercial Applications

One potential commercial application could be in the development of advanced computing systems for data-intensive tasks.

Possible Prior Art

One possible prior art could be similar systems used in signal processing or neural network applications.

Unanswered Questions

How does the processor determine the threshold value for dividing input vector data by output vector data?

The abstract does not provide details on how the threshold value is determined by the processor.

What specific types of memory elements are used in the crossbar array system?

The abstract does not specify the exact types of memory elements employed in the system.


Original Abstract Submitted

A crossbar array includes a number of memory elements. An analog-to-digital converter (ADC) is electronically coupled to the vector output register. A digital-to-analog converter (DAC) is electronically coupled to the vector input register. A processor is electronically coupled to the ADC and to the DAC. The processor may be configured to determine whether division of input vector data by output vector data from the crossbar array is within a threshold value, and if not within the threshold value, determine changed data values as between the output vector data and the input vector data, and write the changed data values to the memory elements of the crossbar array.