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

    'Brake Control Device And Motor Drive Device' in Patent Application Approval Process (USPTO 20240056003)

    148-152页
    查看更多>>摘要：A patent application by the inventor ISHIDA, Hitoshi (Yamanashi, JP), filed on March 24, 2022, was made available online on February 15, 2024, according to news reporting originating from Washington, D.C., by NewsRx correspondents. This patent application has not been assigned to a company or institution. The following quote was obtained by the news editors from the background information supplied by the inventors: “A non-excitation actuated type brake device actuates a brake in a non-excitation state in which no voltage is applied to a brake coil, and releases the brake in an excitation state in which the voltage is applied to the brake coil. “For example, as an electromagnetic brake control device that controls a non-excitation actuated type electromagnetic brake, an electromagnetic brake control device is known that includes an output terminal for connecting the electromagnetic brake, and a brake control unit that outputs a brake control signal to be supplied to the electromagnetic brake via the output terminal, the brake control unit outputting a brake control signal to release the electromagnetic brake when a normal brake command and a safe brake command are both ON, and outputting a brake control signal to actuate the electromagnetic brake when at least one of the normal brake command and the safe brake command is OFF (see, e.g., PTL 1).
      原文链接:
    • NETL
    • NSTL

    Researchers Submit Patent Application, 'Identifying Defects in Optical Detector Systems Based on Extent of Stray Light', for Approval (USPTO 20240056565)

    152-155页
    查看更多>>摘要：From Washington, D.C., NewsRx journalists report that a patent application by the inventors Grabe, Volker (Redwood City, CA, US); Lu, Chen David (Campbell, CA, US); Rinehart, Matthew (San Mateo, CA, US), filed on October 23, 2023, was made available online on February 15, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information supplied by the inventors: “Unless otherwise indicated herein, the materials described in this section are not prior art to the claims in this application and are not admitted to be prior art by inclusion in this section. “Cameras and image sensors are devices used to capture images of a scene. Some cameras (e.g., film cameras) chemically capture an image on film. Other cameras (e.g., digital cameras) electrically capture image data (e.g., using a charge-coupled device (CCD) or complementary metal-oxide-semiconductor (CMOS) sensors). Images captured by cameras can be analyzed to determine their contents. For example, a processor may execute a machine-learning algorithm in order to identify objects in a scene based on a library of previously classified objects that includes objects’ shapes, colors, sizes, etc. (e.g., such a machine-learning algorithm can be applied in computer vision in robotics or other applications).
      原文链接:
    • NETL
    • NSTL

    Patent Issued for Increasing user interaction with deep learning agent (USPTO 11900110)

    155-158页
    查看更多>>摘要：According to news reporting originating from Alexandria, Virginia, by NewsRx journalists, a patent by the inventors Golding, Paul (San Francisco, CA, US), filed on March 19, 2021, was published online on February 13, 2024. The assignee for this patent, patent number 11900110, is Prosper Funding LLC (San Francisco, California, United States). Reporters obtained the following quote from the background information supplied by the inventors: “Computing systems may be used to interact with users with multiple types of communication, including voice communications, email communications, web page communications, etc. A challenge is for computing systems and machine learning systems to identify and use the context of previous communications in subsequent communications.” In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “In general, in one or more aspects, the disclosure relates to a method that increases user interaction with deep learning agents. A generation request for a content slot is received. A subsequent tag vector, for the content slot, is generated from a previous tag, for a previous content slot, using a subsequent tag model. A context vector is generated from a set of subsequent tag vectors, which include the subsequent tag vector, using a context vector generator. A selection vector is generated from the context vector using a contextual bandit model. A content set is generated for a content slot using the selection vector. The content set for the content slot is presented.
      原文链接:
    • NETL
    • NSTL

    Patent Issued for Automated fastening system (USPTO 11897141)

    158-160页
    查看更多>>摘要：From Alexandria, Virginia, NewsRx journalists report that a patent by the inventors Chevalier, Mark (Andover, MN, US), Denney, Jon (Woodbury, MN, US), Goodyear, Case (Scandia, MN, US), Vang, Jerry (Fridley, MN, US), filed on November 19, 2019, was published online on February 13, 2024. The patent’s assignee for patent number 11897141 is Palletec LLC (Fridley, Minnesota, United States). News editors obtained the following quote from the background information supplied by the inventors: “In automated manufacturing, operational speed, accuracy, and process uptime are paramount concerns. Processing speed and uptime are essential for maximizing factory resources (e.g., floor space, energy, etc.) and return on investment (ROI) in the assembly equipment and facilities. Accuracy is essential to reducing process stoppages and costly rework operations, and impacts the quality of the manufactured articles. “As an example, in the manufacture of furniture such as seating and bedding pieces, a mesh structure is typically fastened to a frame structure. The frame structure may be of any suitable material, such as natural wood, or manufactured or recycled material, such as plywood, fiberboard, particle board, plastic, composite material, or metal. The mesh structure is typically a wire mesh, which may carry springs or other structures. To accomplish the fastening in this example, staples are driven over wires of the mesh structure into the frame structure to secure the former to the latter at multiple fastening sites.
      原文链接:
    • NETL
    • NSTL

    Distinct hippocampal mechanisms support concept formation and updating

    160-161页
    查看更多>>摘要：According to news reporting based on a preprint abstract, our journalists obtained the following quote sourced from biorxiv.org: “Learning systems must constantly decide whether to create new representations or update existing ones. For example, a child learning that a bat is a mammal and not a bird would be best served by creating a new representation, whereas updating may be best when encountering a second similar bat. Characterizing the neural dynamics that underlie these complementary memory operations requires identifying the exact moments when each operation occurs. “We address this challenge by interrogating fMRI brain activation with a computational learning model that predicts trial-by-trial when memories are created versus updated. “We found distinct neural engagement in anterior hippocampus and ventral striatum for model-predicted memory create and update events during early learning. Notably, the degree of this effect in hippocampus, but not ventral striatum, significantly related to learning outcome. Hippocampus additionally showed distinct patterns of functional coactivation with ventromedial prefrontal cortex and angular gyrus during memory creation and premotor cortex during memory updating.
      原文链接:
    • NETL
    • NSTL

    Multi-ancestry polygenic risk scores using phylogenetic regularization

    161-161页
    查看更多>>摘要：According to news reporting based on a preprint abstract, our journalists obtained the following quote sourced from biorxiv.org: “Accurately predicting phenotype using genotype across diverse ancestry groups remains a significant challenge in human genetics. Many state-of-the-art polygenic risk score models are known to have difficulty generalizing to genetic ancestries that are not well represented in their training set. “To address this issue, we present a novel machine learning method for fitting genetic effect sizes across multiple ancestry groups simultaneously, while leveraging prior knowledge of the evolutionary relationships among them. “We introduce DendroPRS, a machine learning model where SNP effect sizes are allowed to evolve along the branches of the phylogenetic tree capturing the relationship among populations. DendroPRS outperforms existing approaches at two important genotype-to-phenotype prediction tasks: expression QTL analysis and polygenic risk scores.
      原文链接:
    • NETL
    • NSTL