Patents by Inventor Robert Lajos

Robert Lajos has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20230325662
    Abstract: A computer implemented method for determining a representative input data set for post-training quantization of artificial neural networks comprises: acquiring an input data set; processing the input data set to extract one or more parameters associated with the input data set; setting clipping limits comprising a lower clipping limit and an upper clipping limit; adapting the upper and lower clipping limits by computing (656) a quantization error based on a numerical difference between the input data set and a quantized and a dequantized input data set, wherein the error is computed based on an error metric which is based on user input; and determining a representative input data set as a subset of the input data set whose elements fit within the clipping limits; wherein the representative input data set is to be used for quantization calibration of the post-training quantization.
    Type: Application
    Filed: March 31, 2023
    Publication date: October 12, 2023
    Inventors: Robert Lajos BUCS, Miguel Angel AGUILAR, Soeren KREINBERG
  • Publication number: 20230325636
    Abstract: A computer implemented method for adapting an artificial neural network graph, the method comprising: acquiring an input artificial neural network graph; carrying out a global manipulation step comprising a first set of manipulations configured to adapt the input artificial neural network graph based on at least one user-defined criterion to generate a first intermediate artificial neural network graph; dissecting the first intermediate artificial neural network graph to generate a plurality of second intermediate artificial neural network graphs based on a specification file; and carrying out a respective local manipulation step for each of the plurality of second intermediate artificial neural network graphs, wherein each local manipulation step comprises a corresponding second set of manipulations configured to adapt a corresponding second intermediate artificial neural network graph based on at least one corresponding user-defined criterion and generate a corresponding manipulated second intermediate arti
    Type: Application
    Filed: March 21, 2023
    Publication date: October 12, 2023
    Inventors: Robert Lajos BUCS, Miguel Angel AGUILAR
  • Patent number: 4526665
    Abstract: The subject invention is a method of sputtering a material on a substrate in which the substrate is first locally heated so that the mobility on the surface of the substrate is increased to a value E.sub.s. A material is then sputtered on the substrate with a sputtering energy E.sub.k whereby the sum of E.sub.k and E.sub.s is greater than the activation energy required for a chemical reaction to occur between the sputtered surface of the substrate and the sputtered material. In the preferred embodiment, the substrate is silicon and the material to be sputtered is a refractory metal such as titanium.
    Type: Grant
    Filed: August 20, 1984
    Date of Patent: July 2, 1985
    Assignee: Gould Inc.
    Inventors: Minas Tanielian, Scott Blackstone, Robert Lajos