Vector-matrix multiplication
AssigneeLenslet Labs Ltd.
InventorsAvner Goren, Aviram Sariel, Shimon Levit, Yosefa Asaf, Sergio Liberman, Benzion Sender, Tzvi Tzelnick, Yaron Hefetz, Eyal Moses, Vered Machal
Life of this patent
Estimating the term…
Abstract
An integrated VMM (vector-matrix multiplier) module, including an electro-optical VMM component that multiplies an input vector by a matrix to produce an output vector; and an electronic VPU (vector processing unit) that processes at least one of the input and output vectors. Various error reducing mechanisms are also discussed.
Claims38
An integrated VMM (vector-matrix multiplier) module, comprising:
- an electro-optical VMM component that multiplies an input vector by a matrix to produce an output vector;
- an electronic VPU (vector processing unit) that digitally processes digital data comprised in at least one of the input and output vectors;
- and
- a memory that stores at least one of matrix replacement values, at least one previous output vector and instructions for a component of the module.
An integrated VMM (vector-matrix multiplier) module, comprising:
- a electro-optical VMM component that multiplies an input vector by a matrix to produce an output vector;
- and
- a controller, wherein said controller is operative to replace values in only a part of said matrix.
A method of improving signal detection in an electro-optical VMM, comprising:
- receiving an input vector and a matrix to be processed by said VMM;
- and
- rearranging said input vector on an input of said VMM and said matrix in a matrix portion of said VMM, in a manner that improves signal detection.
A method of improving signal detection in an electro-optical VMM, comprising:
- receiving an input vector and a matrix to be processed by said VMM;
- and
- adapting values of at least one of said input vector on an input of said VMM and said matrix in a matrix portion of said VMM, in a manner that improves signal detection.
A method of improving signal detection in an electro-optical VMM, comprising:
- receiving an input vector and a matrix to be processed by said VMM;
- processing said vector by said VMM to produce an output vector;
- and
- adapting values of said output vector, by applying a history correction which corrects for residual affects of a previous computation performed by said VMM.
Dependencies are inferred from the claim text.