Abstract: An electronic device includes a memory storing computer-readable instructions and at least one processor that coupled to the memory and configured to execute the computer-readable instructions. The at least one processor is configured to identify one or more merge layers included in a pruning target model of a neural network and generate a target group including a target merge layer among the one or more merge layers and a sub-layer logically connected with the target merge layer. The processor is configured to apply a learnable mask to the target group and update the learnable mask, through propagation of the pruning target model. The processor is also configured to perform pruning of the pruning target model based on the updated learnable mask.

Abstract: An electronic device includes a memory storing computer-executable instructions and at least one processor coupled to the memory and configured to execute the computer-readable instructions. The at least one processor is configured to identify a merge layer included in a pruning target model of a neural network to determine a target group including layers, including the merge layer and a sub-layer logically connected with the merge layer. The at least one processor is configured to apply a learnable parameter to each of the layers included in the target group. The at least one processor is configured updates the learnable parameter through propagation of the pruning target model. The at least one processor is configured to perform pruning of the pruning target model based on the updated learnable parameter.

Abstract: Disclosed are an auction method and system, an advertising method and system, and a charging method and system, based on a bid price depending on a time period, and a fixed unit price depending on clicks or exposures. The advertising method may include verifying an advertisement exposure priority determined with respect to an advertisement of an advertiser, based on a period-based bid price which may be input from the advertiser, and exposing the advertisement of the advertiser during a time period corresponding to the period-based bid price, through an advertisement exposure region depending on the verified advertisement exposure priority, wherein an advertising fee depending on the exposure of the advertisement may be calculated based on the period-based bid price, a unit price per click (or a unit price per exposure) determined through an administrator system, and a number of clicks (or a number of exposures) which may actually occur during the time period.

Abstract: Disclosed are an auction method and system, an advertising method and system, and a charging method and system, based on a bid price depending on clicks or exposures, and a fixed unit price depending on a time period.

Abstract: Disclosed are an auction method and system, an advertising method and system, and a charging method and system, based on bid prices depending on clicks or exposures, and a time period. The advertising method may include verifying an advertisement exposure priority determined with respect to an advertisement of an advertiser, based on a bid price per click (or a bid price per exposure), and a period-based bid price which may be input from the advertiser, and exposing the advertisement of the advertiser during a time period corresponding to the period-based bid price, through an advertisement exposure region depending on the verified advertisement exposure priority, wherein an advertising fee depending on the exposure of the advertisement may be calculated based on the bid price per click (or the bid price per exposure), a number of clicks (or a number of exposures) which may actually occur with respect to the advertisement during the time period, and the period-based bid price.