US 2026/0187444 A1Published application

Data modification in an artificial intelligence system

AssigneeMultiverse Computing S.L.

InventorsKurt UYGAR, Saeed JAHROMI, Roman ORUS

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method comprising: processing an instruction to modify a trained artificial intelligence, AI, system, the trained AI system having the form of a tensor network, the instruction comprising adding a first dataset in the AI system and/or removing a second dataset from the AI system; and running the instruction on the trained AI system. When the instruction comprises adding the first dataset, encoding data values of the first dataset in one or more tensors of the trained AI system associated with values of the first dataset. When the instruction comprises removing the second dataset, setting to zero values associated with data values or relationships of the second dataset in one or more tensors of the trained AI system associated with values of the second dataset, or removing the one or more tensors associated with values of the second dataset from the AI system.

Claims20

Dependent claims

An apparatus comprising at least one processor and at least one memory module, the at least one processor and the at least one memory module being configured to:

process an instruction to modify a trained artificial intelligence, AI, system, the AI system being configured to provide at least one output based on an input dataset, wherein the trained AI system has the form of a tensor network, and wherein the instruction comprises at least one of adding a first dataset in the AI system, or removing a second dataset from the AI system;
and
run the instruction on the trained AI system;
wherein the at least one processor and the at least one memory module are configured to run the instruction on the trained AI system by:
encoding data values of the first dataset in one or more tensors of the trained AI system associated with values of the first dataset when the instruction at least comprises adding the first dataset;
and
setting to zero values associated with data values or relationships of the second dataset in one or more tensors of the trained AI system associated with values of the second dataset or removing the one or more tensors associated with values of the second dataset from the AI system when the instruction at least comprises removing the second dataset.

4 more elements

A method comprising:

processing an instruction to modify a trained artificial intelligence, AI, system, the AI system being configured to provide at least one output based on an input dataset, wherein the trained AI system has the form of a tensor network, and wherein the instruction comprises at least one of adding a first dataset in the AI system, or removing a second dataset from the AI system;
and
running the instruction on the trained AI system;
wherein running the instruction on the trained AI system comprises:
when the instruction at least comprises adding the first dataset, encoding data values of the first dataset in one or more tensors of the trained AI system associated with values of the first dataset;
and
when the instruction at least comprises removing the second dataset, setting to zero values associated with data values or relationships of the second dataset in one or more tensors of the trained AI system associated with values of the second dataset, or removing the one or more tensors associated with values of the second dataset from the AI system.

4 more elements

Dependencies are inferred from the claim text.