View source for 20240054330. EXPLOITATION OF LOW DATA DENSITY OR NONZERO WEIGHTS IN A WEIGHTED SUM COMPUTER simplified abstract (COMMISSARIAT A L’ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES)

=EXPLOITATION OF LOW DATA DENSITY OR NONZERO WEIGHTS IN A WEIGHTED SUM COMPUTER=


==Organization Name==

[[:Category:COMMISSARIAT A L’ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES|COMMISSARIAT A L’ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES]]


[[Category:COMMISSARIAT A L’ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES]]

==Inventor(s)==

[[:Category:Michel Harrand of GRENOBLE (FR)|Michel Harrand of GRENOBLE (FR)]][[Category:Michel Harrand of GRENOBLE (FR)]]

==EXPLOITATION OF LOW DATA DENSITY OR NONZERO WEIGHTS IN A WEIGHTED SUM COMPUTER - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240054330 titled 'EXPLOITATION OF LOW DATA DENSITY OR NONZERO WEIGHTS IN A WEIGHTED SUM COMPUTER

==Simplified Explanation==

The abstract describes a computing circuit that calculates a weighted sum of a set of first data using parsimony management circuits. The circuit includes buffer memories for storing the first and second data delivered sequentially, as well as processing circuits for analyzing the data and controlling its transfer to a distribution circuit based on skip indicators.

* The computing circuit computes a weighted sum of first data using parsimony management circuits.
* The circuit includes buffer memories for storing first and second data delivered sequentially.
* Processing circuits analyze the data to find non-zero data and define skip indicators between successive non-zero data.
* The transfer of data to the distribution circuit is controlled based on the skip indicators.

---

### Potential Applications
* Signal processing applications
* Data compression algorithms
* Machine learning algorithms

### Problems Solved
* Efficient management of data transfer
* Reduction of unnecessary data processing
* Improved computing circuit performance

### Benefits
* Increased efficiency in computing weighted sums
* Reduced memory usage
* Enhanced performance in data analysis and processing


==Original Abstract Submitted==

a computing circuit for computing a weighted sum of a set of first data using at least one parsimony management circuit includes a first buffer memory for storing all or some of the first data delivered sequentially and a second buffer memory for storing all or some of the second data delivered sequentially. the parsimony management circuit furthermore comprises a first processing circuit able: to analyze the first data in order to search for the first non-zero data and define a first skip indicator between two successive non-zero data, and to control the transfer, to the distribution circuit, of a first datum read from the first data buffer memory on the basis of the first skip indicator. the parsimony management circuit furthermore comprises a second processing circuit able to control the transfer, to the distribution circuit, of a second datum read from the second data buffer memory on the basis of the first skip indicator.



[[Category:G06N3/063]]