Patents by Inventor Yuchen Bian

Yuchen Bian has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20230084203
    Abstract: Model pruning is used to trim large neural networks, like convolutional neural networks (CNNs), to reduce computation overheads. Existing model pruning methods mainly rely on heuristics rules or local relationships of CNN layers. A novel hypernetwork based on graph neural network is disclosed for generating and evaluating pruned networks. A graph is first constructed according to information flow of channels and layers in a CNN network, with channels and layers represented as nodes and information flows represented as edges. A graph neural network is applied to aggregate both local and global dependencies across all channels and layers of the CNN network, resulting in informative node embeddings. With such embeddings, pruned CNN networks including their architectures and weights may be effectively generated and evaluated.
    Type: Application
    Filed: June 22, 2022
    Publication date: March 16, 2023
    Applicant: Baidu USA LLC
    Inventors: Baopu LI, Qiuling SUO, Yuchen BIAN
  • Publication number: 20220108773
    Abstract: COVID-19 has become a global pandemic after its inception in late 2019. SARS-CoV-2 genomes are sequenced and shared on public repositories at a fast pace. To keep up with these updates, datasets need to be refreshed and re-cleaned frequently. It may be difficult to analyze SARS-CoV-2 genomes for scientists with limited bioinformatics or programming knowledge. In the present disclosure, system and method embodiments for genome analysis and visualization are developed to address these challenges. A webserver may be used to enable simple and rapid analysis of genomes. Given a new sequence, the system may automatically predict gene boundaries and identify genetic variants, which are presented in an interactive genome visualizer and are downloadable for analysis. A command-line interface may be available for high throughput processing.
    Type: Application
    Filed: October 7, 2020
    Publication date: April 7, 2022
    Applicant: Baidu USA LLC
    Inventors: Boxiang LIU, Kaibo LIU, He ZHANG, Liang ZHANG, Yuchen BIAN, Liang HUANG
  • Patent number: 11249887
    Abstract: Systems and methods for automated software test design and implementation. The system and method being able to establish an initial pool of test cases for testing computer code; apply the initial pool of test cases to the computer code in a testing environment to generate test results; preprocess the test results into a predetermined format; extract metadata from the test results; generate a training sequence; calculate a reward value for the pool of test cases; input the training sequence and reward value into a reinforcement learning agent; utilizing the value output from the reinforcement learning agent to produce a ranking list; prioritizing the initial pool of test cases and one or more new test cases based on the ranking list; and applying the prioritized initial pool of test cases and one or more new test cases to the computer code in a testing environment to generate test results.
    Type: Grant
    Filed: August 20, 2020
    Date of Patent: February 15, 2022
    Inventors: Jianwu Xu, Haifeng Chen, Yuchen Bian
  • Publication number: 20210064515
    Abstract: Systems and methods for automated software test design and implementation. The system and method being able to establish an initial pool of test cases for testing computer code; apply the initial pool of test cases to the computer code in a testing environment to generate test results; preprocess the test results into a predetermined format; extract metadata from the test results; generate a training sequence; calculate a reward value for the pool of test cases; input the training sequence and reward value into a reinforcement learning agent; utilizing the value output from the reinforcement learning agent to produce a ranking list; prioritizing the initial pool of test cases and one or more new test cases based on the ranking list; and applying the prioritized initial pool of test cases and one or more new test cases to the computer code in a testing environment to generate test results.
    Type: Application
    Filed: August 20, 2020
    Publication date: March 4, 2021
    Inventors: Jianwu Xu, Haifeng Chen, Yuchen Bian