G06K1/00

Reinforcement learning for training compression policies for machine learning models

A compression policy to produce compression profiles for compressing trained machine learning models may be trained using reinforcement learning. An iterative reinforcement learning may be performed response to a search request. Different prospective compression profiles may be generated for received machine learning models according to a compression policy being trained. Performance of compressed versions of the trained neural networks according to the compression profiles may be caused using data sets used to train the machine learning models. The compression policy may be updated according to reward signal determined from an application of a reward function for performance criteria to performance results of the different versions of the machine learning models. When a search criteria is satisfied, the trained compression policy may be provided.

System and method for server connection using multiple network adapters
11575800 · 2023-02-07 ·

A system and method for managing print services between multifunction peripherals and a print server includes a connector server. The connector server subscribes to event notifications from each multifunction peripheral through two or more network adapters. Events are relayed from the connector server to the print server, irrespective as to which network adapter receives them. The connector server also relays web content between the multifunction peripheral and the print server.

Automatic machine learning feature backward stripping
11494699 · 2022-11-08 · ·

Features are used to train one or more ML models in a modelling layer. In a feature selection layer, each generated ML model is analyzed to determine, for each input feature, a degree of importance of the feature on the results generated by the ML model. Features with low importance are identified and the information is propagated backward to the data source and feature engineering layers. In response, the data source and feature engineering layers refrain from gathering or generating the unimportant features. Based on a confidence measure of the determination that each feature is important or unimportant, a number of periods between reevaluation of the feature importance is determined. After the number of periods has elapsed, a removed feature is restored to the pipeline.

System for changing wireless communication settings at reserved locations

An information processing apparatus includes a changing unit. The changing unit changes a setting of wireless communication in a location in accordance with a user who has made a reservation for the location.

Systems and methods for operating an imaging device

The various embodiments illustrated herein disclose a method for operating an imaging device. the method includes activating a first image sensor at a first duty cycle within a first time period. The method further includes activating a second image sensor at a second duty cycle within the first time period. Additionally, the method includes modifying at least one of the first duty cycle or the second duty cycle based on at least a workflow associated an operator of the imaging device.

Terminal device that displays progress of a process in chat style
11609725 · 2023-03-21 · ·

Disclosed is a screen display method for providing display, on a display screen included in a terminal device, for a given process to be performed for an image processing apparatus. The screen display method includes displaying, in a chat style, a plurality of instructions regarding the given process and a plurality of responses to the instructions, and providing progress display indicating a progress of the given process.

Information processing apparatus that determines whether a format of near field communication tag data is appropriate, method of controlling the same, and non-transitory computer-readable medium
11483438 · 2022-10-25 · ·

An information processing apparatus capable of executing near field wireless communication, comprises: a display unit configured to display a screen; an obtaining unit configured to obtain identification information regarding a device from a near field wireless communication tag with use of the near field wireless communication; a selection unit configured, in a case where the obtaining unit obtained the identification information, to select one of first processing for connecting to the device indicated by the identification information and second processing for connecting to the device indicated by the identification information and sending data to the device, based on a type of screen being displayed by the display unit; and a processing unit configured to execute the processing selected by the selection unit.

Information processing apparatus, control method, and storage medium
11481169 · 2022-10-25 · ·

In a case where a registration state of a printing apparatus in operating system (OS) standard print software and a registration state of the printing apparatus in print conversion software do not match each other, an information processing apparatus performs a process for matching between a registration state of a print queue of the printing apparatus in the OS standard print software and the registration state of the printing apparatus in the print conversion software.

Method and apparatus for rapidly classifying defects in subcomponents of manufactured component
11475556 · 2022-10-18 · ·

The present disclosure provides methods and apparatus for rapidly classifying detected defects in subcomponents of a manufactured component or device. The defect classification may occur after defect detection or, because the classification may be sufficiently rapid to be performed in real-time, during defect detection, as part of the defect detection process. In an exemplary implementation, the presently-disclosed technology may be utilized to enable real-time classification of detected defects in multiple subcomponents of the component in parallel. The component may be, for example, a multi-chip package with silicon interposers, and the subcomponents may include, for example, through-silicon vias and solder joints. Defects in subcomponents of other types of components may be also be classified. One embodiment relates to a method of classifying detected defects in subcomponents of a manufactured component. Another embodiment relates to a product manufactured using a disclosed method of inspecting multiple subcomponents of a component for defects.

Multifunction peripheral with exterior member different from input unit

A multifunction peripheral includes an exterior member that corresponds to an exterior portion of the multifunction peripheral and that differs from an input unit that inputs an instruction for a program, a reception unit that receives an instruction for performing a process that involves an operation of the exterior member, and a notification unit that notifies a user of a position on the exterior member to be operated by the user of the multifunction peripheral when the process is performed in a case where the reception unit receives the instruction for performance.