18334271. METHOD FOR OPERATING NEURAL NETWORK (NATIONAL TSING HUA UNIVERSITY)

From WikiPatents
Revision as of 07:35, 19 December 2024 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

METHOD FOR OPERATING NEURAL NETWORK

Organization Name

NATIONAL TSING HUA UNIVERSITY

Inventor(s)

Kea Tiong Tang of Taipei City (TW)

Kuan-Pei Lee of Tainan City (TW)

METHOD FOR OPERATING NEURAL NETWORK

This abstract first appeared for US patent application 18334271 titled 'METHOD FOR OPERATING NEURAL NETWORK



Original Abstract Submitted

A method is provided and includes operations as below: receiving an input in an input layer of a spiking neural network during time steps, wherein the input includes multiple spikes; generating, based on multiple activation values corresponding to the spikes, location information including count numbers each corresponding to non-zero values, in the activation values, in one of multiple rows of the input; performing, based on the location information, a matrix multiplication with the non-zero values in a first number of rows in the rows with a first group of filters of weight values to generate multiple first membrane potentials for outputting a first output spike; and performing, based on the location information, the matrix multiplication with the non-zero values in a second number of rows in the rows with the first group of filters of weight values to generate multiple second membrane potentials for outputting a second output spike.