Patents by Inventor Hsin I. Tseng

Hsin I. Tseng 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).

  • Quantizing feature vectors in decision-making applications
    Patent number: 8271278
    Abstract: A system, method and computer program product for classification of an analog electrical signal using statistical models of training data. A technique is described to quantize the analog electrical signal in a manner which maximizes the compression of the signal while simultaneously minimizing the diminution in the ability to classify the compressed signal. These goals are achieved by utilizing a quantizer designed to minimize the loss in a power of the log-likelihood ratio. A further technique is described to enhance the quantization process by optimally allocating a number of bits for each dimension of the quantized feature vector subject to a maximum number of bits available across all dimensions.
    Type: Grant
    Filed: April 3, 2010
    Date of Patent: September 18, 2012
    Assignee: International Business Machines Corporation
    Inventors: Upendra V. Chaudhari, Hsin I. Tseng, Deepak S. Turaga, Olivier Verscheure
  • Quantizing feature vectors in decision-making applications
    Patent number: 7769583
    Abstract: A system, method and computer program product for classification of an analog electrical signal using statistical models of training data. A technique is described to quantize the analog electrical signal in a manner which maximizes the compression of the signal while simultaneously minimizing the diminution in the ability to classify the compressed signal. These goals are achieved by utilizing a quantizer designed to minimize the loss in a power of the log-likelihood ratio. A further technique is described to enhance the quantization process by optimally allocating a number of bits for each dimension of the quantized feature vector subject to a maximum number of bits available across all dimensions.
    Type: Grant
    Filed: May 13, 2006
    Date of Patent: August 3, 2010
    Assignee: International Business Machines Corporation
    Inventors: Upendra V. Chaudhari, Hsin I. Tseng, Deepak S. Turaga, Olivier Verscheure
  • QUANTIZING FEATURE VECTORS IN DECISION-MAKING APPLICATIONS
    Publication number: 20100191531
    Abstract: A system, method and computer program product for classification of an analog electrical signal using statistical models of training data. A technique is described to quantize the analog electrical signal in a manner which maximizes the compression of the signal while simultaneously minimizing the diminution in the ability to classify the compressed signal. These goals are achieved by utilizing a quantizer designed to minimize the loss in a power of the log-likelihood ratio. A further technique is described to enhance the quantization process by optimally allocating a number of bits for each dimension of the quantized feature vector subject to a maximum number of bits available across all dimensions.
    Type: Application
    Filed: April 3, 2010
    Publication date: July 29, 2010
    Applicant: International Business Machines Corporation
    Inventors: Upendra V. CHAUDHARI, Hsin I. Tseng, Deepak S. Turaga, Olivier Verscheure