中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

1145 records (took 0.024 seconds)

    Image transformation with a hybrid autoencoder and generative adversarial network machine learning architecture
    113.
    发明授权
    Image transformation with a hybrid autoencoder and generative adversarial network machine learning architecture 有权

    公开(公告)号：US10803347B2

    公开(公告)日：2020-10-13

    申请号：US16206538

    申请日：2018-11-30

    Applicant: The University of Chicago

    Inventor： Jason Salavon

    IPC: G06K9/62 ,  G06F16/55 ,  G06N3/08 ,  G06N3/04 ,  G06F16/583

    Abstract: An encoder artificial neural network (ANN) may be configured to receive an input image patch and produce a feature vector therefrom. The encoder ANN may have been trained with a first plurality of domain training images such that an output image patch visually resembling the input image patch can be generated from the feature vector. A generator ANN may be configured to receive the feature vector and produce a generated image patch from the first feature vector. The generator ANN may have been trained with feature vectors derived from a first plurality of domain training images and a second plurality of generative training images such that the generated image patch visually resembles the input image patch but is constructed of a newly-generated image elements visually resembling one or more image patches from the second plurality of generative training images.

    Training Artificial Neural Networks Using Context-Dependent Gating with Weight Stabilization
    118.
    发明申请
    Training Artificial Neural Networks Using Context-Dependent Gating with Weight Stabilization 审中-公开

    公开(公告)号：US20200250483A1

    公开(公告)日：2020-08-06

    申请号：US16774343

    申请日：2020-01-28

    Applicant: The University of Chicago

    Inventor： Nicolas Y. Masse ,  Gregory D. Grant ,  David J. Freedman

    IPC: G06K9/62 ,  G06N3/04

    Abstract: A computing device may receive a first set of training data for training an ANN to predict output data for a first task, and may train the ANN with the first set of training data by only adjusting values of weights associated with a first subset of neurons, the first subset selected based on an identity of the first task. The computing device may receive a second, different set of training data for training the ANN to predict output data for a second task, and may train the ANN with the second set of training data by only adjusting values of weights associated with a second subset of neurons, the second subset selected based on an identity of the second task. During training, adjusting of the value of any weight may entail weight stabilization that depends on whether there has been any training for one or more previous tasks.

    Methanothermobacter Thermautotrophicus Strain and Variants Thereof
    119.
    发明申请
    Methanothermobacter Thermautotrophicus Strain and Variants Thereof 审中-公开

    公开(公告)号：US20200248207A1

    公开(公告)日：2020-08-06

    申请号：US16574984

    申请日：2019-09-18

    Applicant: THE UNIVERSITY OF CHICAGO

    Inventor： Laurens Mets

    IPC: C12P5/02 ,  C12N1/20 ,  C12N13/00 ,  C12R1/01 ,  C12N15/01

    Abstract: Provided herein is an isolated Methanothermobacter microorganism that is (a) a microorganism of Methanothermobacter thermautotrophicus strain UC 120910, deposited on Dec. 21, 2010, with the American Type Culture Collection (ATCC) under ATCC® Patent Deposit Designation No. PTA-11561, (b) a variant of the microorganism of Methanothermobacter thermautotrophicus strain UC 120910, or (c) a progeny of the microorganism of Methanothermobacter thermautotrophicus strain UC 120910, wherein the variant or progeny retains the phenotypic characteristics of the microorganism of Methanothermobacter thermautotrophicus strain UC 120910. Also provided herein is a substantially pure culture or monoculture comprising the Methanothermobacter microorganism of the disclosure. A system for converting electric power into methane, comprising a biological reactor having at least a cathode, an anode, a presently disclosed Methanothermobacter microorganism, water, and carbon dioxide, and method of using the system for converting electricity into methane are further provided herein.

Patent Agency Ranking