US Patent Application 18187577. INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND STORAGE MEDIUM simplified abstract
Contents
INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND STORAGE MEDIUM
Inventors
INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND STORAGE MEDIUM - A simplified explanation of the abstract
- This abstract for appeared for patent application number 18187577 Titled 'INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND STORAGE MEDIUM'
Simplified Explanation
The present disclosure introduces a method for optimizing the structure of a neural network to achieve accurate results without increasing processing requirements. An information processing apparatus is used to learn the architecture of the neural network. It generates multiple potential options for an edge of the network and applies these options as weight coefficients during the learning process. The apparatus then evaluates the inference results and calculates a loss for the neural network based on a specified number of selected candidates. The weight coefficients are updated based on this loss. Finally, the apparatus selects candidates from the pool of options based on the updated weight coefficients.
Original Abstract Submitted
The present disclosure makes it possible to learn a neural network architecture for achieving a sufficient inference accuracy while preventing an increase in the amount of processing. An information processing apparatus configured to learn an architecture for optimizing a structure of a neural network generates a plurality of candidates for an edge of the neural network, inputs learning data to the neural network with weight coefficients set to these candidates for the edge, and obtains an inference result. The information processing apparatus calculates a loss of the neural network based on a specified candidate number which is the number of candidates to be selected from the plurality of candidates and on the inference result, and then updates the weight coefficients for the plurality of candidates based on the loss. The information processing apparatus then selects candidates from the plurality of candidates based on the updated weight coefficients.
