Patents by Inventor Sekitoshi KANAI

Sekitoshi KANAI 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: 20210326705
    Abstract: A learning apparatus (10) includes: a generation unit (11) configured having a mathematical model for generating data through an input of a random number used for deep learning to a nonlinear function; and a prior learning unit (13) configured to cause the generation unit (11) to execute prior learning of a variance and an average using unscented transform (UT). The prior learning unit (13) estimates, using UT, the variance and the average of data generated by the generation unit (11) and updates a parameter of the generation unit (11) to minimize an evaluation function for evaluating a similarity between the estimated variance and average and a variance and an average of true data calculated in advance.
    Type: Application
    Filed: August 13, 2019
    Publication date: October 21, 2021
    Inventor: Sekitoshi KANAI
  • Publication number: 20210056418
    Abstract: A calculation unit (121) calculates, for an output signal of an output layer in a neural network, an output function obtained by replacing an exponential function included in softmax with a product of the exponential function and a predetermined function having no parameter, the output function having a non-linear log likelihood function. An update unit (122) updates a parameter of the neural network on the basis of the output signal such that the log likelihood function of the output function is optimized.
    Type: Application
    Filed: April 22, 2019
    Publication date: February 25, 2021
    Inventors: Sekitoshi KANAI, Yasuhiro FUJIWARA, Yuki YAMANAKA