Systems and Methods for Activation Functions for Photonic Neural Networks
US-2021116781-A1 · Apr 22, 2021 · US
US8935115B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-8935115-B2 |
| Application number | US-201213412176-A |
| Country | US |
| Kind code | B2 |
| Filing date | Mar 5, 2012 |
| Priority date | Mar 4, 2011 |
| Publication date | Jan 13, 2015 |
| Grant date | Jan 13, 2015 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A method and apparatus for compensating nonlinear damage are disclosed. The method for compensating nonlinear damage, including: determining an additive parameter indicating an amount of nonlinear damage based on a plurality of sampled signal sets among which a sampling time of an input signal varies according to different time; and subtracting the additive parameter from the input signal.
Opening claim text (preview).
The invention claimed is: 1. A method for compensating nonlinear damage, comprising: determining an additive parameter indicating an amount of nonlinear damage based on a plurality of sampled signal sets among which a sampling time of an input signal varies according to different time; and subtracting the additive parameter from the input signal. 2. The method according to claim 1 , wherein the determining the additive parameter comprises: sampling by acq…
Electricity · mapped topic
Electricity · mapped topic
Related publications grouped by family.
Free tools are coming soon. Tell us what you want to track and we'll notify you.
Answers are generated from the same data shown on this page.