首页期刊导航|Robotics & Machine Learning Daily News
期刊信息/Journal information
Robotics & Machine Learning Daily News
NewsRx
Robotics & Machine Learning Daily News

NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News
正式出版
收录年代

    Patent Application Titled 'Weak Supervised Training Data For Image Tagging Model s' Published Online (USPTO 20240378863)

    254-257页
    查看更多>>摘要:Reporters obtained the following quote from the background information supplied by the inventors:“The following relates generally to machine learning, and more specifically to machine learning for imagetagging.“Digital image processing generally refers to the process of making changes to a digital image ormetadata of the digital image using a computer or other electr onic device. A computer or other electronicdevice may use an algorithm, a proce ssing network, etc. to make changes to a digital image or metadataof the digita l image. In some cases, image processing software may be used for various image processingtasks, such as image editing, image generation, image tagging, etc. S ome image processing systemsmay implement machine learning techniques, for exam ple, to perform tasks using predictive models (e.g.,without explicitly programi ng the system for each task), to perform tasks with more accuracy or in lesstim e, to perform tasks using special-purpose hardware, etc.”

    Patent Application Titled 'Classification Parallelization Architecture' Publishe d Online (USPTO 20240378880)

    257-261页
    查看更多>>摘要:Reporters obtained the following quote from the background information supplied by the inventors:“Stable and reliable robotic systems are becoming increasingly common, which has contributed to therecent advancement and proliferation of un manned system technologies. These technologies can beground-based systems, acri al-based systems, and/or maritime-based systems. In many instances thesesystems are equipped with one or more cameras, one or more microphones, and/or other re cordingequipment. The image/sound stream from the unmanned system(s) may be sen t to an operator’s controldevice to make the operator aware of what is happenin g on the ground. In many cases it may be usefulfor the image stream to be annot ated with different objects detected within the video/audio stream.Currently, o bjects within images/sound frames are generally detected using machine learning models.These machine learning models are generally hosted on dedicated hardware with dedicated data sources.However, in operational scenarios it may be critic al to use third-party models (e.g., from entities that areable to train those m odels because those entities have the required training data). Moreover, operato rsin the field may want to choose which object types need to be detected for a particular operation becauseindicating other object types may interfere with th e operator being able to assess the operational situation.Thus, enabling this f unctionality on an unmanned vehicle or another device with limited computation resources is challenging at best.”

    Patent Application Titled 'Optimized Artificial Intelligence Search System And M ethod For Providing Content In Response To Search Queries' Published Online (USP TO 20240378249)

    261-266页
    查看更多>>摘要:Reporters obtained the following quote from the background information supplied by the inventors:“Search engines implement computerized search algorithms to al low users to search resources such asrelevant websites or databases. The search engines are configured to locate resources that are relevant to the search quer y or queries. Users enter a search query consisting of strings of alphanumeric c haractersor words. The search query can take forms ranging from a single search term (or query) to a complexsentence composed in a natural language. When used in conjunction with the search engine, the wordconcept generally refers to a c onstruct such as a cluster of related words associated with a keyword.

    Researchers Submit Patent Application, 'Systems And Methods For Mitigating The S pread Of Offensive Content And/Or Behavior', for Approval (USPTO 20240380721)

    266-270页
    查看更多>>摘要:News editors obtained the following quote from the background information suppli ed by the inventors:“Electronic messaging systems have enabled instant, and pub lic, sharing messages across many users andcommunities of users easy. With a cl ick of a button, a user can make content available for towns, cities,states, an d even nations to view. Accordingly, when that content includes offensive conten t, the impactof that offensive content can be wide-ranging.”

    Patent Application Titled 'Gesture Training For Skill Adaptation And Accessibili ty' Published Online (USPTO 20240377894)

    271-273页
    查看更多>>摘要:Reporters obtained the following quote from the background information supplied by the inventors:“Certain computer simulations such as certain computer game (b oth virtual reality (VR) and non-VR)assume a certain level of dexterity from th eir players. This could involve moving a motion controller in acertain path, at a certain speed (in the case of a gesture for example) in a VR game such as Bea t Saberor The Wizards, or it could include pressing a button repeatedly in a co mbat game to break free from anopponent. As understood herein, some players may have difficulty performing these actions either becausethe actions are difficu lt to master or because the players have a physical disability which prevents th emfrom executing the actions.”

    Decrypting the complex phenotyping traits of plants by machine learning

    273-274页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – According to news reporting based on a preprint abstract, our journalists obtained thefollowing quote sourced from bi orxiv.org: “Phenotypes, defining an organism\’s behaviour and phy sical attributes, arise from the complex,dynamic interplay of genetics, develop ment, and environment, whose interactions make it enormouslychallenging to fore cast future phenotypic traits of a plant at a given moment.

    Ultrafast elastocapillary fans control agile maneuvering in ripple bugs and robo ts

    274-275页
    查看更多>>摘要:By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews – According to news reporting based on a preprint a bstract, our journalists obtained the followingquote sourced from biorxiv.org:“Millimeter-sized ripple bugs in the genus Rhagovelia exhibit exceptional agilit y and rapid maneuversin fast, unsteady streams, comparable to animal fliers. Th eir remarkable interfacial transit and turningskills stem from a specialized fa n structure on their middle legs. While researchers have suggested activefan ac tuation, the role of capillary forces and unique microstructure in self-spreadin g remains unclear.“We reveal that Rhagovelia\’s fans possess a flat-ribb on architecture with directional stiffness, enablingultrafast elastocapillary m orphing for passive actuation in under 10 ms, independent of muscle control,whi le producing high-thrust momentum through unsteady vortical wakes.