公开(公告)号：US11899787B2

公开(公告)日：2024-02-13

申请号：US16819532

申请日：2020-03-16

Applicant: HITACHI, LTD.

Inventor： Tadayuki Matsumura

IPC: G06N3/047 ,  G06F21/55 ,  G06N5/04 ,  G06F18/214 ,  G06F18/21 ,  G06F18/2413 ,  G06N3/045 ,  G06V10/74 ,  G06V10/762 ,  G06V10/778 ,  G06V10/82 ,  G06V10/44

CPC classification number: G06F21/554 ,  G06F18/214 ,  G06F18/217 ,  G06F18/24137 ,  G06F21/55 ,  G06N3/045 ,  G06N3/047 ,  G06N5/04 ,  G06V10/454 ,  G06V10/761 ,  G06V10/763 ,  G06V10/7796 ,  G06V10/82

Abstract: To provide a robust information processing system against attacks by Adversarial Example. A neural network model 608, a latent space database 609 for storing position information in a latent space in which first output vectors, which are output vectors of a predetermined hidden layer included in the neural network model, are embedded concerning input data used for learning of the neural network model, and an inference control unit 606 for making an inference using the neural network model and the latent space database are provided. The inference control unit infers the input data based on the positional relationship between the second output vector, which is an output vector of the predetermined hidden layer concerning input data to be inferred, and the first output vectors in said latent space.

公开(公告)号：US11899722B2

公开(公告)日：2024-02-13

申请号：US16971292

申请日：2018-06-20

Applicant: RAKUTEN GROUP, INC.

Inventor： Yeongnam Chae

IPC: G06V10/82 ,  G06F16/903 ,  G06T7/70 ,  G06F16/55 ,  G06F16/53 ,  G06N3/08 ,  G06F18/22 ,  G06F18/211 ,  G06F18/2413 ,  G06N3/042 ,  G06V10/74 ,  G06V10/764

CPC classification number: G06F16/90335 ,  G06F16/53 ,  G06F16/55 ,  G06F18/211 ,  G06F18/22 ,  G06F18/2413 ,  G06N3/042 ,  G06N3/08 ,  G06T7/70 ,  G06V10/761 ,  G06V10/764 ,  G06V10/82

Abstract: To improve accuracy of search, a learner (L) of a search system calculates a feature quantity of information that is input and outputs a first analysis result of the information in a first viewpoint and a second analysis result of the information in a second viewpoint based on the feature quantity. Storing means stores a feature quantity of information to be searched, which has been input in the learner (L), in a database. Input means inputs input information in the learner (L). Search means searches for information to be searched that is similar to the input information in the feature quantity based on the database.

公开(公告)号：US20240047011A1

公开(公告)日：2024-02-08

申请号：US18488691

申请日：2023-10-17

Applicant: The Broad Institute, Inc. ,  Massachusetts Institute of Technology

Inventor： Feng Zhang ,  David Arthur Scott

IPC: G16B40/00 ,  G16B20/00 ,  G16B20/50 ,  G16B40/30 ,  G16B20/30 ,  G06F18/231 ,  G06F18/20 ,  G06F18/2413

CPC classification number: G16B40/00 ,  G16B20/00 ,  G16B20/50 ,  G16B40/30 ,  G16B20/30 ,  G06F18/231 ,  G06F18/295 ,  G06F18/2413 ,  G06N3/088

Abstract: Embodiments disclosed herein provide methods for identifying new CRISPR loci and effectors, as well as different CRISPR loci combinations found in various organisms. Class-II CRISPR systems contain single-gene effectors that have been engineered for transformative biological discovery and biomedical applications. Discovery of additional single-gene or multicomponent CRISPR effectors may enhance existing CRISPR applications, such as precision genome engineering. Comprehensive characterization of CRISPR-loci may identify novel functional roles of CRISPR loci enabling new tools for biomedicine and biological discovery. CRISPR loci have enormous feature complexity, but classification of CRISPR loci has been focused on a small fraction of highly abundant features. Increased genome sequencing has enhanced the sampling of this feature complexity.

公开(公告)号：US20240046483A1

公开(公告)日：2024-02-08

申请号：US18489278

申请日：2023-10-18

Applicant: STATS LLC

Inventor： Long Sha ,  Sujoy Ganguly ,  Xinyu Wei ,  Patrick Joseph Lucey ,  Aditya Cherukumudi

IPC: G06T7/20 ,  G06N3/08 ,  G06T7/73 ,  G06T7/80 ,  G06T7/00 ,  G06T7/70 ,  H04N21/44 ,  G06V20/40 ,  G06V40/20 ,  G06F18/22 ,  G06F18/214 ,  G06F18/232 ,  G06F18/2135 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/82 ,  G06V10/44

CPC classification number: G06T7/20 ,  G06N3/08 ,  G06T7/73 ,  G06T7/80 ,  G06T7/97 ,  G06T7/70 ,  H04N21/44008 ,  G06V20/42 ,  G06V20/46 ,  G06V20/48 ,  G06V20/49 ,  G06V40/20 ,  G06F18/22 ,  G06F18/214 ,  G06F18/232 ,  G06F18/2135 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/82 ,  G06V10/454 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/10016 ,  G06T2207/30221 ,  G06T2207/30244 ,  G06V20/44

Abstract: A system and method of generating a player tracking prediction are described herein. A computing system retrieves a broadcast video feed for a sporting event. The computing system segments the broadcast video feed into a unified view. The computing system generates a plurality of data sets based on the plurality of trackable frames. The computing system calibrates a camera associated with each trackable frame based on the body pose information. The computing system generates a plurality of sets of short tracklets based on the plurality of trackable frames and the body pose information. The computing system connects each set of short tracklets by generating a motion field vector for each player in the plurality of trackable frames. The computing system predicts a future motion of a player based on the player's motion field vector using a neural network.

公开(公告)号：US20240045861A1

公开(公告)日：2024-02-08

申请号：US18168045

申请日：2023-02-13

Applicant: SK hynix Inc.

Inventor： Joon Seop SIM ,  Eui Cheol LIM

IPC: G06F16/2453 ,  G06F18/2413

CPC classification number: G06F16/2453 ,  G06F18/24147

Abstract: A system for classifying data may include a memory, and a processor configured to determine a scan target including a data group selected from among data groups stored in the memory, based on a result of a comparison between first similarities of data groups stored in the memory and an externally received query, and a minimum value of second similarities of pieces of data included in a data group having a maximum value of the first similarities and the query, and to output, as result data responding to the query, scan data selected depending on a reference number of pieces of scan data from among pieces of scan data in the data group included in the scan target.

公开(公告)号：US11895220B2

公开(公告)日：2024-02-06

申请号：US17176530

申请日：2021-02-16

Applicant: TripleBlind, Inc.

Inventor： Greg Storm ,  Riddhiman Das ,  Babak Poorebrahim Gilkalaye

IPC: H04L9/00 ,  G06F17/16 ,  H04L9/40 ,  H04L9/06 ,  G06Q20/40 ,  G06Q30/0601 ,  G06Q20/12 ,  G06V10/764 ,  G06V10/82 ,  G06V10/44 ,  G06N3/04 ,  G06N3/082 ,  G06F18/24 ,  G06F18/2113 ,  G06F18/2413

CPC classification number: H04L9/008 ,  G06F17/16 ,  G06Q20/1235 ,  G06Q20/401 ,  G06Q30/0623 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  H04L9/0625 ,  H04L63/0428 ,  G06F18/2113 ,  G06F18/24 ,  G06F18/24133 ,  G06N3/04 ,  G06N3/082 ,  G06Q2220/00 ,  H04L2209/46

Abstract: A method includes dividing a plurality of filters in a first layer of a neural network into a first set of filters and a second set of filters, applying each of the first set of filters to an input of the neural network, aggregating, at a second layer of the neural network, a respective one of a first set of outputs with a respective one of a second set of outputs, splitting respective weights of specific neurons activated in each remaining layer, at each specific neuron from each remaining layer, applying a respective filter associated with each specific neuron and a first corresponding weight, obtaining a second set of neuron outputs, for each specific neuron, aggregating one of the first set of neuron outputs with one of a second set of neuron outputs and generating an output of the neural network based on the aggregated neuron outputs.

公开(公告)号：US11887363B2

公开(公告)日：2024-01-30

申请号：US17279924

申请日：2019-09-27

Applicant: Google LLC

Inventor： Soeren Pirk ,  Yunfei Bai ,  Pierre Sermanet ,  Seyed Mohammad Khansari Zadeh ,  Harrison Lynch

IPC: G06V20/10 ,  B25J9/16 ,  B25J13/00 ,  G05B13/02 ,  G06N3/08 ,  G10L15/22 ,  G06F18/21 ,  G06F18/2413 ,  G06V10/764 ,  G06V10/70 ,  G06V10/776 ,  G06V10/82

CPC classification number: G06V20/10 ,  B25J9/1697 ,  B25J13/003 ,  G05B13/027 ,  G06F18/217 ,  G06F18/2413 ,  G06N3/08 ,  G06V10/764 ,  G06V10/768 ,  G06V10/776 ,  G06V10/82 ,  G10L15/22

Abstract: Training a machine learning model (e.g., a neural network model such as a convolutional neural network (CNN) model) so that, when trained, the model can be utilized in processing vision data (e.g., from a vision component of a robot), that captures an object, to generate a rich object-centric embedding for the vision data. The generated embedding can enable differentiation of even subtle variations of attributes of the object captured by the vision data.

公开(公告)号：US20240020951A1

公开(公告)日：2024-01-18

申请号：US18352168

申请日：2023-07-13

Applicant: Blue River Technology Inc.

Inventor： Lee Kamp Redden ,  Christopher Grant Padwick ,  Rajesh Radhakrishnan ,  James Patrick Ostrowski

IPC: G06V10/764 ,  G06T7/00 ,  A01M7/00 ,  G06T7/73 ,  G06V20/10 ,  G06V10/20 ,  G06V10/44 ,  G06V20/20 ,  G06F18/2413

CPC classification number: G06V10/764 ,  G06T7/0002 ,  A01M7/0089 ,  G06T7/75 ,  G06V20/188 ,  G06V10/255 ,  G06V10/451 ,  G06V20/20 ,  G06F18/2414 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30188 ,  G06T2210/12 ,  G06T2207/20132 ,  G06T2207/10024

Abstract: A plant treatment platform uses a plant detection model to detect plants as the plant treatment platform travels through a field. The plant treatment platform receives image data from a camera that captures images of plants (e.g., crops or weeds) growing in the field. The plant treatment platform applies pre-processing functions to the image data to prepare the image data for processing by the plant detection model. For example, the plant treatment platform may reformat the image data, adjust the resolution or aspect ratio, or crop the image data. The plant treatment platform applies the plant detection model to the pre-processed image data to generate bounding boxes for the plants. The plant treatment platform then can apply treatment to the plants based on the output of the machine-learned model.

公开(公告)号：US11875561B2

公开(公告)日：2024-01-16

申请号：US18107876

申请日：2023-02-09

Applicant: X Development LLC

Inventor： Ananya Gupta ,  Phillip Ellsworth Stahlfeld ,  Bangyan Chu

IPC: G06V20/10 ,  G06T7/50 ,  G06T7/73 ,  G06F30/18 ,  G06F16/587 ,  G06F16/29 ,  G06T5/30 ,  G06T7/60 ,  G06T11/20 ,  G06T17/05 ,  H02J3/00 ,  G06F18/2413

CPC classification number: G06V20/182 ,  G06F16/29 ,  G06F16/587 ,  G06F18/24133 ,  G06F30/18 ,  G06T5/30 ,  G06T7/50 ,  G06T7/60 ,  G06T7/73 ,  G06T7/75 ,  G06T11/206 ,  G06T17/05 ,  G06V20/176 ,  H02J3/00 ,  G06T2207/10032 ,  G06T2207/30184 ,  G06V20/194 ,  H02J2203/20

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage device, for electric grid asset detection are enclosed. An electric grid asset detection method includes: obtaining overhead imagery of a geographic region that includes electric grid wires; identifying the electric grid wires within the overhead imagery; and generating a polyline graph of the identified electric grid wires. The method includes replacing curves in polylines within the polyline graph with a series of fixed lines and endpoints; identifying, based on characteristics of the fixed lines and endpoints, a location of a utility pole that supports the electric grid wires; detecting an electric grid asset from street level imagery at the location of the utility pole; and generating a representation of the electric grid asset for use in a model of the electric grid.

公开(公告)号：US20240007822A1

公开(公告)日：2024-01-04

申请号：US18369770

申请日：2023-09-18

Applicant: CLIMATE LLC

Inventor： Mark YOUNG

IPC: H04W4/021 ,  G06N20/00 ,  G05D1/02 ,  G06V20/10 ,  G06V20/56 ,  G06V30/24 ,  G06F18/2413 ,  G06V10/70

CPC classification number: H04W4/021 ,  G06N20/00 ,  G05D1/0246 ,  G06V20/188 ,  G06V20/56 ,  G06V30/2504 ,  G06F18/2413 ,  G06V10/87 ,  G06V20/10 ,  G05D2201/0201

Abstract: Autonomous vehicles with global positioning systems are used for field inspection. A vehicle may be programmed to traverse a field, while using sensors to detect objects in the field, and then capture low-resolution images of the objects. Machine vision techniques are used with the low-resolution images to recognize the objects as crops, non-crop plant material or undefined objects. Location data is used to correlate recognized objects with digitally stored field maps to resolve whether a particular object is in a location at which crop planting is expected or not expected. Depending on whether an object in a low-resolution digital image is recognized as a crop, and whether the object is in an expected geo-location for crops, the vehicle may switch to a second image capture mode, for example, capturing a high-resolution image of the object, and/or execute a disease analysis and/or weed analysis on the images of the objects.