-
公开(公告)号：US11704534B2
公开(公告)日：2023-07-18
申请号：US16221612
申请日：2018-12-17
Applicant: Industrial Technology Research Institute
Inventor： Ching-Hao Lai , Mao-Yu Huang
IPC: G06F18/245 , G06F18/2113 , G06N3/02 , G06N3/04
CPC classification number: G06N3/02 , G06F18/2113 , G06F18/245 , G06N3/04
Abstract: Provided is a neural-network-based classification method, including: generating, by a neural network, one or more score vectors corresponding to one or more samples respectively; determining a first subset of the one or more samples according to the one or more score vectors and a first decision threshold, wherein the first subset is associated with a first class; and selecting samples to be re-examined from the one or more samples according to the first subset.
-
公开(公告)号：US10902314B2
公开(公告)日：2021-01-26
申请号：US16182619
申请日：2018-11-07
Applicant: Industrial Technology Research Institute
Inventor： Mao-Yu Huang
Abstract: A neural network-based classification method, including: obtaining a neural network and a first classifier; inputting input data to the neural network to generate a feature map; cropping the feature map to generate a first cropped part and a second cropped part of the feature map; inputting the first cropped part to the first classifier to generate a first probability vector; inputting the second cropped part to a second classifier to generate a second probability vector, wherein weights of the first classifier are shared with the second classifier; and performing a probability fusion on the first probability vector and the second probability vector to generate an estimated probability vector for determining a class of the input data.
-
公开(公告)号：US10474925B2
公开(公告)日：2019-11-12
申请号：US15793086
申请日：2017-10-25
Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE
Inventor： Mao-Yu Huang , Ching-Hao Lai
Abstract: A deep neural network and a method for recognizing and classifying a multimedia data as one of a plurality of pre-determined data classes with enhanced recognition and classification accuracy and efficiency are provided. The use of the side branch(es) (or sub-side branch(es), sub-sub-side branch(es), and so on) extending from the main branch (or side branch(es), sub-side branch(es), and so on), the sequential decision making mechanism, and the collaborating (fusing) decision making mechanism in a deep neural network would equip a deep neural network with the capability for fast forward inference so as to enhance recognition and classification accuracy and efficiency of the deep neural network.
-
Patent Agency Ranking
公开(公告)号：US20210174200A1
公开(公告)日：2021-06-10
申请号：US16729453
申请日：2019-12-29
Applicant: Industrial Technology Research Institute
Inventor： Mao-Yu Huang , Po-Yen Hsieh , Chih-Neng Liu , Tsann-Tay Tang
IPC: G06N3/08 , G06N3/04 , G01N21/956 , G06T7/00
Abstract: A training device and a training method for a neural network model are provided. The training method includes: obtaining a data set; completing, according to the data set, a plurality of artificial intelligence (AI) model trainings to generate a plurality of models corresponding to the plurality of AI model trainings respectively; selecting, according to a first constraint, a first model set from the plurality of models; and selecting, according to a second constraint, the neural network model from the first model set.
-
公开(公告)号：US20230118614A1
公开(公告)日：2023-04-20
申请号：US17534340
申请日：2021-11-23
Applicant: Industrial Technology Research Institute
Inventor： Mao-Yu Huang , Sen-Chia Chang , Ming-Yu Shih , Tsann-Tay Tang , Chih-Neng Liu
Abstract: An electronic device and a method for training a neural network model are provided. The method includes: obtaining a first neural network model and a first pseudo-labeled data; inputting the first pseudo-labeled data into the first neural network model to obtain a second pseudo-labeled data; determining whether a second pseudo-label corresponding to the second pseudo-labeled data matching a first pseudo-label corresponding to the first pseudo-labeled data; in response to the second pseudo-label matching the first pseudo-label, adding the second pseudo-labeled data to a pseudo-labeled dataset; and training the first neural network model according to the pseudo-labeled dataset.
-
公开(公告)号：US10970604B2
公开(公告)日：2021-04-06
申请号：US16211240
申请日：2018-12-06
Applicant: Industrial Technology Research Institute
Inventor： Mao-Yu Huang
Abstract: A fusion-based classifier, classification method, and classification system, wherein the classification method includes: generating a plurality of probability vectors according to input data, wherein each of the plurality of probability vectors includes a plurality of elements corresponding to a plurality of class respectively; selecting, from the plurality of probability vectors, a first probability vector having an extremum value corresponding to a first class-of-interest according to the first class-of-interest; and determining a class of the input data according to the first probability vector.
-
公开(公告)号：US11636336B2
公开(公告)日：2023-04-25
申请号：US16729453
申请日：2019-12-29
Applicant: Industrial Technology Research Institute
Inventor： Mao-Yu Huang , Po-Yen Hsieh , Chih-Neng Liu , Tsann-Tay Tang
IPC: G06N3/08 , G01N21/956 , G06T7/00 , G06N3/045
Abstract: A training device and a training method for a neural network model. The training method includes: obtaining a data set; completing, according to the data set, a plurality of artificial intelligence (AI) model trainings to generate a plurality of models corresponding to the plurality of AI model trainings respectively; selecting, according to a first constraint, a first model set from the plurality of models; and selecting, according to a second constraint, the neural network model from the first model set.
-
公开(公告)号：US20200090028A1
公开(公告)日：2020-03-19
申请号：US16182619
申请日：2018-11-07
Applicant: Industrial Technology Research Institute
Inventor： Mao-Yu Huang
Abstract: A neural network-based classification method, including: obtaining a neural network and a first classifier; inputting input data to the neural network to generate a feature map; cropping the feature map to generate a first cropped part and a second cropped part of the feature map; inputting the first cropped part to the first classifier to generate a first probability vector; inputting the second cropped part to a second classifier to generate a second probability vector, wherein weights of the first classifier are shared with the second classifier; and performing a probability fusion on the first probability vector and the second probability vector to generate an estimated probability vector for determining a class of the input data.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.013 seconds)
