-
公开(公告)号：WO2010003044A2
公开(公告)日：2010-01-07
申请号：PCT/US2009/049487
申请日：2009-07-02
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MALON, Christopher , MILLER, Matthew, L.
CPC classification number: G06K9/4628 , G06K9/0014 , G06K9/00147 , G06K9/2018
Abstract: An epithelial detector and method for automatically identifying epithelial portions of a tissue sample, includes: staining the tissue sample with at least two dyes; applying a color transformation to a color image of the tissue sample to obtain one or more color channels; and applying a trained convolutional neural network to the color channels to obtain a decision for position in the tissue as to whether it is inside or outside an epithelial layer. Also, a method for training the convolutional neural network.
Abstract translation: 用于自动识别组织样品的上皮部分的上皮检测器和方法包括：用至少两种染料染色组织样品; 对组织样本的彩色图像应用颜色变换以获得一个或多个颜色通道; 以及将经过训练的卷积神经网络应用于所述颜色通道以获得关于所述组织中位于所述组织内是否在上皮层内部或外部的位置的决定。 另外，一种训练卷积神经网络的方法。
-
公开(公告)号：WO2021119082A1
公开(公告)日：2021-06-17
申请号：PCT/US2020/063937
申请日：2020-12-09
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MIN, Renqiang , MALON, Christopher , GRAF, Hans, Peter
Abstract: Methods and systems for disentangled data generation include accessing (310) a dataset including pairs, each formed from a given input text structure and a given style label for the input text structures. An encoder is trained (360) to disentangle a sequential text input into disentangled representations, including a content embedding and a style embedding, based on a subset of the dataset, using an objective function that includes a regularization term that minimizes mutual information between the content embedding and the style embedding. A generator is trained (360) to generate a text output that includes content from the style embedding, expressed in a style other than that represented by the style embedding of the text input.
-
公开(公告)号：WO2021062052A1
公开(公告)日：2021-04-01
申请号：PCT/US2020/052577
申请日：2020-09-24
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： KRUUS, Erik , MALON, Christopher , LIU, Bingyuan
Abstract: Aspects of the present disclosure describe improving neural network robustness through neighborhood preserving layers and learning weighted-average neighbor embeddings. A method of training a neural network comprises modifying gradient backpropagation of weighted-average neighbor layer into input domain entries. The present disclosure may adapt certain manifold representation techniques to an online setting that advantageously affords practical real world benefits including uses in machine learning application for training neural networks in applications desiring dimension reduction, interpretability, smoothness, and acting as a form of regularization providing benefit against adversarial attack.
-
公开(公告)号：WO2022216935A1
公开(公告)日：2022-10-13
申请号：PCT/US2022/023840
申请日：2022-04-07
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MIN, Renqiang , MELVIN, Iain , WHITE, Christopher A , MALON, Christopher , GRAF, Hans Peter
Abstract: Systems and methods for matching job descriptions with job applicants is provided. The method includes allocating each of one or more job applicants curriculum vitae (CV) into sections 320; applying max pooled word embedding 330 to each section of the job applicants CVs; using concatenated max-pooling and average-pooling 340 to compose the section embeddings into an applicants CV representation; allocating each of one or more job position descriptions into specified sections 220; applying max pooled word embedding 230 to each section of the job position descriptions; using concatenated max-pooling and average-pooling 240 to compose the section embeddings into a job representation; calculating a cosine similarity 250, 350 between each of the job representations and each of the CV representations to perform job-to-applicant matching; and presenting an ordered list of the one or more job applicants 360 or an ordered list of the one or more job position descriptions 260 to a user.
-
Patent Agency Ranking
公开(公告)号：WO2021126664A1
公开(公告)日：2021-06-24
申请号：PCT/US2020/064275
申请日：2020-12-10
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MALON, Christopher , JOSHI, Nitish
IPC: G06N20/00 , G06N5/04 , G06F40/30 , G06K9/6223 , G06K9/6262 , G06N5/045
Abstract: A method trains (410) an inference model on two-hop NLI problems that include a first and second premise and a hypothesis, and further includes generating (420), by the model using hypothesis reduction, an explanation from an input premise and an input hypothesis, for an input single hop NLI problem. The learning step determines a distribution over extraction starting positions and lengths from within the first premise and hypothesis of a two-hop NLI problem. The learning step k extraction output slots with combinations of words from the first premise of the two-hop NLI problem and fills another extraction output slots with combinations of words from the hypothesis of the two-hop NLI problem. The learning step trains a sequence model by using the extraction output slots and the other extraction output slots together with the second premise as an input to a single-hop NLI classifier to output a label of the two-hop NLI problem.
-
6.发明申请
公开(公告)号：WO2021119074A1
公开(公告)日：2021-06-17
申请号：PCT/US2020/063926
申请日：2020-12-09
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MIN, Renqiang , MALON, Christopher , PENGYU, Cheng
Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing (310), by a bidirectional Long Short-Term Memory (LSTM) with a multi-head attention mechanism, a dataset including a plurality of pairs each formed from a given one of a plurality of input text structures and given one of a plurality of style labels for the plurality of input text structures. The method further includes training (320) the bidirectional LSTM as an encoder to disentangle a sequential text input into disentangled representations comprising a content embedding and a style embedding based on a subset of the dataset. The method also includes training (350) a unidirectional LSTM as a decoder to generate a next text structure prediction for the sequential text input based on previously generated text structure information and a current word, from a disentangled representation with the content embedding and the style embedding.
-
7.发明申请
公开(公告)号：WO2021113467A1
公开(公告)日：2021-06-10
申请号：PCT/US2020/063045
申请日：2020-12-03
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MALON, Christopher , BAI, Bing
IPC: G06F16/332 , G06F16/242 , G06F16/35 , G06F16/28 , G06N3/04 , G06N20/00
Abstract: A computer-implemented method is provided for generating following up questions for multi-hop bridge-type question answering. The method includes retrieving (310) a premise for an input multi-hop bridge-type question. The method further includes assigning (320), by a three-way neural network based controller, a classification of the premise against the input multi-hop bridge-type question as being any of irrelevant, including a final answer, or including intermediate information. The method also includes outputting (330) the final answer in relation to a first hop of the multi-hop bridge-type question responsive to the classification being including the final answer. The method additionally includes generating (350) a followup question by a neural network and repeating said retrieving, assigning, outputting and generating steps for the followup question, responsive to the classification being including the intermediate information.
-
公开(公告)号：WO2010003043A2
公开(公告)日：2010-01-07
申请号：PCT/US2009/049486
申请日：2009-07-02
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MALON, Christopher , MILLER, Matthew, L , COSATTO, Eric
CPC classification number: G06K9/00147 , G01N1/312 , G06T7/0012 , G06T2207/20061 , G06T2207/20081 , G06T2207/20084 , G06T2207/30024
Abstract: A detector and method for automatically detecting signet ring cells in an image of a biopsy tissue sample, includes finding in the image, points about which cell membranes appear in radial symmetry; selecting as candidate points, at least ones of the points that have an adjacent nuclei with a predetermined shape feature; and applying a convolutional neural network to the candidate points to determine which of the candidate points are signet ring cells.
Abstract translation: 用于在活检组织样本的图像中自动检测印戒细胞的检测器和方法包括在图像中发现关于哪个细胞膜呈径向对称的点; 选择候选点，具有具有预定形状特征的相邻核的点中的至少一个; 以及向所述候选点应用卷积神经网络，以确定所述候选点中的哪一个是所述环形蜂窝小区。
-
公开(公告)号：EP2257636A2
公开(公告)日：2010-12-08
申请号：EP09774493.2
申请日：2009-07-02
Applicant: NEC Laboratories America, Inc.
Inventor： MALON, Christopher , MILLER, Matthew, L.
CPC classification number: G06K9/4628 , G06K9/0014 , G06K9/00147 , G06K9/2018
Abstract: An epithelial detector and method for automatically identifying epithelial portions of a tissue sample, includes: staining the tissue sample with at least two dyes; applying a color transformation to a color image of the tissue sample to obtain one or more color channels; and applying a trained convolutional neural network to the color channels to obtain a decision for position in the tissue as to whether it is inside or outside an epithelial layer. Also, a method for training the convolutional neural network.
Abstract translation: 用于自动识别组织样本的上皮部分的上皮检测器和方法包括：用至少两种染料对组织样本进行染色; 对组织样本的彩色图像应用颜色变换以获得一个或多个颜色通道; 以及将训练的卷积神经网络应用于颜色通道以获得组织中位置的决定，以确定其位于上皮层内部还是外部。 此外，还提供了一种训练卷积神经网络的方法。
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.026 seconds)
