专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

61. 发明申请

US20230114736A1 SYSTEM AND METHOD FOR VISUALIZING GOALS, RELATIONSHIPS, AND PROGRESS 有权
公开(公告)号：US20230114736A1
公开(公告)日：2023-04-13
申请号：US17499805
申请日：2021-10-12
申请人： TOYOTA RESEARCH INSTITUTE, INC.
发明人： Shabnam Hakimi , Matthew Len Lee , Charlene C. Wu , Nikos Arechiga
IPC分类号： G06Q10/00 , G06N3/04 , G06T19/00 , G02B27/01
摘要： A method for goal progression and visualization is described. The method includes generating a graph-like structure according to user specified goals along with their associated timeframes and desired outcomes. The method also includes converting the graph-like structure into a topological landscape of hills and valleys representing the user specified goals along with the associated timeframes and desired outcomes. The method further includes displaying the topological landscape of hills and valleys representing the user specified goals along with the associated timeframes and desired outcomes.

62. 发明申请

US20230114551A1 OPTICAL DEVICE AND OPTICAL NEURAL NETWORK APPARATUS INCLUDING THE SAME 有权
公开(公告)号：US20230114551A1
公开(公告)日：2023-04-13
申请号：US17990317
申请日：2022-11-18
申请人： SAMSUNG ELECTRONICS CO., LTD.
发明人： Duhyun Lee , Jaeduck Jang
IPC分类号： G06N3/04 , G02B27/10 , G02B27/28 , G02B26/02 , G06N3/067 , G06V10/14 , G06V10/141 , G06V10/145 , G06V10/147 , G06N3/048 , H04N23/73
摘要： Provided are an optical device which is capable of optically implementing an activation function of an artificial neural network and an optical neural network apparatus which includes the optical device. The optical device may include: a beam splitter splitting incident light into first light and second light; an image sensor disposed to sense the first light; an optical shutter configured to transmit or block the second light; and a controller controlling operations of the optical shutter, based on an intensity of the first light measured by the image sensor.

63. 发明申请

US20230113618A1 DETECTION OF UNSAFE CABIN CONDITIONS IN AUTONOMOUS VEHICLES 有权
公开(公告)号：US20230113618A1
公开(公告)日：2023-04-13
申请号：US17982109
申请日：2022-11-07
申请人： Alpine Electronics of Silicon Valley, Inc.
发明人： Rocky Chau-Hsiung Lin , Thomas Yamasaki , Koichiro Kanda
IPC分类号： G06V20/59 , G06N3/04 , G06N3/08 , G08B25/10 , H04W4/44 , B60Q9/00 , B60R22/48 , G06V40/20 , G06F18/24 , G06F18/214
摘要： Devices, systems and processes for the detection of unsafe cabin conditions that provides a safer passenger experience in autonomous vehicles are described. One example method for enhancing passenger safety includes capturing at least a set of images of one or more passengers in the vehicle, determining, based on the set of images, the occurrence of an unsafe activity in an interior of the vehicle, performing, using a neural network, a classification of the unsafe activity, and performing, based on the classification, one or more responsive actions.

64. 发明申请

US20230113271A1 METHODS AND APPARATUS TO PERFORM DENSE PREDICTION USING TRANSFORMER BLOCKS 有权
公开(公告)号：US20230113271A1
公开(公告)日：2023-04-13
申请号：US17855763
申请日：2022-06-30
申请人： Intel Corporation
发明人： Renee Ranftl , Alexey Bochkovskiy , Vladlen Koltun
IPC分类号： G06T3/40 , G06T5/00 , G06N3/04
摘要： Methods, apparatus, systems and articles of manufacture disclosed herein perform dense prediction of an input image using transformers at an encoder stage and at a reassembly stage of an image processing system. A disclosed apparatus includes an encoder with an embedder to convert an input image to a plurality of tokens representing features extracted from the input image. The tokens are embedded with a learnable position embedding. The encoder also includes one or more transformers configured in a sequence of stages to relate the tokens to each other. The apparatus further includes a decoder that includes one or more of reassemblers to assemble the tokens into feature representations, one or more of fusion blocks to combine the feature representations to generate a final feature representation, and an output head to generate a dense prediction based on the final feature representation and based on an output task.

65. 发明申请

US20230113231A1 METHODS AND SYSTEMS OF OPERATING A NEURAL CIRCUIT IN A NON-VOLATILE MEMORY BASED NEURAL-ARRAY 有权
公开(公告)号：US20230113231A1
公开(公告)日：2023-04-13
申请号：US17882348
申请日：2022-08-05
申请人： Vishal Sarin
发明人： Vishal Sarin
IPC分类号： G06N3/063 , G06N3/04 , G06F17/16 , G06F7/499 , G06N3/049 , G06N3/082 , G06N3/065
摘要： In one aspect, a method of a neuron circuit includes the step of providing a plurality of 2N−1 single-level-cell (SLC) flash cells for each synapse (Yi) connected to a bit line forming a neuron. The method includes the step of providing an input vector (Xi) for each synapse Yi wherein each input vector is translated into an equivalent electrical signal ESi (current IDACi, pulse TPULSEi, etc). The method includes the step of providing an input current to each synapse sub-circuit varying from 20*ESi to (2N−1)*ESi. The method includes the step of providing a set of weight vectors or synapse (Yi), wherein each weight vector is translated into an equivalent threshold voltage level or resistance level to be stored in one of many non-volatile memory cells assigned to each synapse (Yi). The method includes the step of providing for 2N possible threshold voltage levels or resistance levels in the 2N−1 non-volatile memory cells of each synapse, wherein each cell is configured to store one of the two possible threshold voltage levels. The method includes the step of converting the N digital bits of the weight vector or synapse Yi into equivalent threshold voltage level and store the appropriate cell corresponding to that threshold voltage level in one of the many SLC cells assigned to the weight vector or synapse (Yi). The method includes the step of turning off all remaining 2N−1 flash cells of the respective synapse (Yi).
Various other methods are presented of forming neuron circuits by providing a plurality of single-level-cell (SLC) and many-level-cell (MLC) non-volatile memory cells, for each synapse (Yi) electrically connected to form a neuron. The disclosure shows methods of forming neurons in various configurations for non-volatile memory cells (flash, RRAM etc.); of different storage capabilities per cell—both SLC and MLC cells.

66. 发明申请

US20230110731A1 SYSTEM, METHOD, AND APPARATUS FOR PROVIDING DYNAMIC, PRIORITIZED SPECTRUM MANAGEMENT AND UTILIZATION 有权
公开(公告)号：US20230110731A1
公开(公告)日：2023-04-13
申请号：US18077802
申请日：2022-12-08
申请人： Digital Global Systems, Inc.
发明人： Armando Montalvo , Bryce Simmons
IPC分类号： H04W16/10 , G06N3/02 , G06N20/20 , G06N20/00 , H04W24/02 , H04W72/04 , H04L41/0893 , G06F30/27 , G06N5/02 , G06N5/04 , G06N20/10 , H04W16/14 , G06N3/04 , H04W24/08 , H04L41/0894
摘要： Systems, methods, and apparatuses for providing dynamic, prioritized spectrum utilization management. The system includes at least one monitoring sensor, at least one data analysis engine, at least one application, a semantic engine, a programmable rules and policy editor, a tip and cue server, and/or a control panel. The tip and cue server is operable utilize the environmental awareness from the data processed by the at least one data analysis engine in combination with additional information to create actionable data.

67. 发明申请

US20230109964A1 Method and System for Training a Neural Network for Generating Universal Adversarial Perturbations 有权
公开(公告)号：US20230109964A1
公开(公告)日：2023-04-13
申请号：US17450476
申请日：2021-10-11
申请人： Mitsubishi Electric Research Laboratories, Inc.
发明人： Ye Wang , Shuchin Aeron , Adnan Rakin , Toshiaki Koike Akino , Pierre Moulin , Kieran Parsons
IPC分类号： G06N3/08 , G06N3/04 , G06K9/62
摘要： Embodiments of the present disclosure disclose a method and a system for training a neural network for generating universal adversarial perturbations. The method includes collecting a plurality of data samples. Each of the plurality of data samples is identified by a label from a finite set of labels. The method includes training a probabilistic neural network for transforming the plurality of data samples into a corresponding plurality of perturbed data samples having a bounded probability of deviation from the plurality of data samples by maximizing a conditional entropy of the finite set of labels of the plurality of data samples conditioned on the plurality of perturbed data samples. The conditional entropy is unknown. The probabilistic neural network is trained based on an iterative estimation of a gradient of the unknown conditional entropy of labels. The method further includes generating the universal adversarial perturbations based on the trained probabilistic neural network.

68. 发明授权

US11627443B2 Apparatus and method for compensating channel based on artificial neural network 有权
公开(公告)号：US11627443B2
公开(公告)日：2023-04-11
申请号：US16657026
申请日：2019-10-18
申请人： Hyundai Motor Company , Kia Motors Corporation , Korea National University of Transportation Industry-Academic Cooperation Foundation
发明人： Zeung Il Kim , Young Cheol Koh , Jae Hun Jeong , Chang Ick Song , Seung Ho Han
IPC分类号： H04B7/00 , H04W4/40 , G06N3/04 , G06N3/088
摘要： An apparatus for compensating a channel based on an artificial neural network includes a channel learning device that learns a property of the channel, and a channel compensating device that compensates for an error of the channel based on a learning result of the channel learning device.

69. 发明授权

US11626966B2 Methods and apparatus for analog canceler tuning using neural networks 有权
公开(公告)号：US11626966B2
公开(公告)日：2023-04-11
申请号：US17109634
申请日：2020-12-02
申请人： Massachusetts Institute of Technology
发明人： Kenneth E. Kolodziej , Aidan U. Cookson , Bradley Thomas Perry
IPC分类号： H04L5/14 , G06N3/04 , H04B17/345
摘要： A network device includes a transceiver configured to concurrently transmit signals and receive signals within a single frequency band resulting in radio-frequency signal interference. The device includes an analog canceler configured to mitigate the signal interference. The device includes a neural network that receives data that describes characteristics of the signal interference and provides coefficients for the analog canceler as outputs. The neural network-generated coefficients are applied to the analog canceler which uses them to cancel the signal interference.

70. 发明授权

US11625921B2 Method and system for detecting and recognizing target in real-time video, storage medium, and device 有权
公开(公告)号：US11625921B2
公开(公告)日：2023-04-11
申请号：US17012761
申请日：2020-09-04
申请人： Tencent Technology (Shenzhen) Company Limited
发明人： Jun Cheng , Haibao Shang , Feng Li , Haoyuan Li , Xiaoxiang Zuo
IPC分类号： G06V20/00 , G06V20/40 , G06T7/70 , G06K9/62 , G06N3/04 , G06N3/08 , G06V40/10
摘要： This disclosure provides a method and a system for detecting and recognizing a target object in a real-time video. The method includes: determining whether a target object recognition result RX-1 of a previous frame of image of a current frame of image is the same as a target object recognition result RX-2 of a previous frame of image of the previous frame of image; performing target object position detection in the current frame of image by using a first-stage neural network to obtain a position range CX of a target object in the current frame of image when the two recognition results RX-1 and RX-2 are different; or determining a position range CX of a target object in the current frame of image according to a position range CX-1 of the target object in the previous frame of image when the two recognition results RX-1 and RX-2 are the same; and performing target object recognition in the current frame of image according to the position range CX by using a second-stage neural network. Therefore, the operating frequency of the first-stage neural network used for position detection is reduced, the recognition speed is accelerated, and the usage of CPU and internal memory resources is reduced.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式