US Patent Application 18295679. INFORMATION PROCESSING APPARATUS, CONTROL METHOD OF INFORMATION PROCESSING APPARATUS, AND STORAGE MEDIUM simplified abstract

From WikiPatents
Jump to navigation Jump to search

INFORMATION PROCESSING APPARATUS, CONTROL METHOD OF INFORMATION PROCESSING APPARATUS, AND STORAGE MEDIUM

Organization Name

CANON KABUSHIKI KAISHA


Inventor(s)

KOICHI Tanji of Kanagawa (JP)


INFORMATION PROCESSING APPARATUS, CONTROL METHOD OF INFORMATION PROCESSING APPARATUS, AND STORAGE MEDIUM - A simplified explanation of the abstract

  • This abstract for appeared for US patent application number 18295679 Titled 'INFORMATION PROCESSING APPARATUS, CONTROL METHOD OF INFORMATION PROCESSING APPARATUS, AND STORAGE MEDIUM'

Simplified Explanation

The abstract describes an information processing apparatus that performs a search for the architecture of a network model. The apparatus includes a first learning unit that learns an architecture coefficient, a second learning unit that learns a weight coefficient, and a control unit that alternates the learning process between the two units. The control unit also allows either unit to learn using a network model's output value as a teacher model, based on coefficients acquired at different points in time.


Original Abstract Submitted

An information processing apparatus which executes a search for an architecture of a network model includes a first learning unit configured to execute learning of an architecture coefficient, a second learning unit configured to execute learning of a weight coefficient, and a control unit configured to execute control to advance the search by causing the first learning unit and the second learning unit to execute learning alternately. The control unit executes control to cause at least any one of the first learning unit and the second learning unit to execute learning on a network model including an architecture coefficient and a weight coefficient acquired at the current point in time using an output value output from a network model set as a teacher model which is configured based on an architecture coefficient and a weight coefficient acquired prior to the current point in time.