-
公开(公告)号：WO2022066388A1
公开(公告)日：2022-03-31
申请号：PCT/US2021/048832
申请日：2021-09-02
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： KADAV, Asim , LAI, Farley , GRAF, Hans, Peter , NICULESCU-MIZIL, Alexandru , MIN, Renqiang , ZHOU, Honglu
Abstract: A method for using a multi-hop reasoning framework to perform multi-step compositional long-term reasoning is presented. The method includes extracting (1001) feature maps and frame-level representations from a video stream by using a convolutional neural network (CNN), performing (1003) object representation learning and detection, linking (1005) objects through time via tracking to generate object tracks and image feature tracks, feeding (1007) the object tracks and the image feature tracks to a multi-hop transformer that hops over frames in the video stream while concurrently attending to one or more of the objects in the video stream until the multi-hop transformer arrives at a correct answer, and employing (1009) video representation learning and recognition from the objects and image context to locate a target object within the video stream.
-
公开(公告)号：WO2020197853A1
公开(公告)日：2020-10-01
申请号：PCT/US2020/023136
申请日：2020-03-17
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： KADAV, Asim , MELVIN, Iain , GRAF, Hans, Peter , HAN, Meera
IPC: G06F16/732 , G06F16/78 , G06F40/20 , G06N3/08
Abstract: A computer-implemented method for performing mini-batching in deep learning by improving cache utilization is presented. The method includes temporally localizing a candidate clip (114) in a video stream (105) based on a natural language query (112), encoding a state, via a state processing module (120), into a joint visual and linguistic representation, feeding the joint visual and linguistic representation into a policy learning module (150), wherein the policy learning module employs a deep learning network to selectively extract features for select frames for video-text analysis and includes a fully connected linear layer (152) and a long short-term memory (LSTM) (154), outputting a value function (156) from the LSTM, generating an action policy based on the encoded state, wherein the action policy is a probabilistic distribution over a plurality of possible actions given the encoded state, and rewarding policy actions that return clips matching the natural language query.
-
公开(公告)号：WO2023038834A1
公开(公告)日：2023-03-16
申请号：PCT/US2022/042172
申请日：2022-08-31
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MIN, Renqiang , GRAF, Hans, Peter , CHEN, Ziqi
Abstract: A system for binding peptide search for immunotherapy is presented. The system includes employing (101) a deep neural network to predict a peptide presentation given Major Histocompatibility Complex allele sequences and peptide sequences, training (103) a Variational Autoencoder (VAE) to reconstruct peptides by converting the peptide sequences into continuous embedding vectors, running (105) a Monte Carlo Tree Search to generate a first set of positive peptide vaccine candidates, running (105) a Bayesian Optimization search with the trained VAE and a Backpropagation search with the trained VAE to generate a second set of positive peptide vaccine candidates, using (107) a sampling from a Position Weight Matrix (sPWM) to generate a third set of positive peptide vaccine candidates, screening and merging (109) the first, second, and third sets of positive peptide vaccine candidates, and outputting (111) qualified peptides for immunotherapy from the screened and merged sets of positive peptide vaccine candidates.
-
公开(公告)号：WO2021211233A1
公开(公告)日：2021-10-21
申请号：PCT/US2021/021849
申请日：2021-03-11
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MIN, Renqiang , YU, Wenchao , GRAF, Hans, Peter , DURDANOVIC, Igor
Abstract: A method is provided for peptide-based vaccine generation. The method receives (210) a dataset of positive and negative binding peptide sequences. The method pre-trains (240) a set of peptide binding property predictors on the dataset to generate training data. The method trains (250) a Wasserstein Generative Adversarial Network (WGAN) only on the positive binding peptide sequences, in which a discriminator of the WGAN is updated to distinguish generated peptide sequences from sampled positive peptide sequences from the training data, and a generator of the WGAN is updated to fool the discriminator. The method trains (260) the WGAN only on the positive binding peptide sequences while simultaneously updating the generator to minimize a kernel Maximum Mean Discrepancy (MMD) loss between the generated peptide sequences and the sampled peptide sequences and maximize prediction accuracies of a set of pre-trained peptide binding property predictors with parameters of the set of pre-trained peptide binding property predictors being fixed.
-
Patent Agency Ranking
公开(公告)号：WO2018052714A2
公开(公告)日：2018-03-22
申请号：PCT/US2017/049327
申请日：2017-08-30
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MALVIN, Iain , COSATTO, Eric , DURDANOVIC, Igor , GRAF, Hans, Peter
CPC classification number: G06K9/4628 , G06K9/00664 , G06K9/00791 , G06K9/6274 , G06K9/6289
Abstract: A computer-implemented method and system are provided. The system includes an image capture device (510) configured to capture image data relative to an ambient environment of a user. The system further includes a processor (511) configured to detect and localize objects, in a real-world map space, from the image data using a trainable object localization Convolutional Neural Network (CNN). The CNN is trained to detect and localize the objects from image and radar pairs that include the image data and radar data for different scenes of a natural environment. The processor (511) is further configured to perform a user-perceptible action responsive to a detection and a localization of an object in an intended path of the user.
Abstract translation: 提供了一种计算机实现的方法和系统。 该系统包括图像捕获设备（510），其被配置成捕获与用户的周围环境相关的图像数据。 该系统还包括处理器（511），其被配置为使用可训练对象定位卷积神经网络（CNN）从图像数据检测和定位真实世界地图空间中的对象。 美国有线电视新闻网的训练是检测和定位来自图像和雷达对的物体，其中包括自然环境不同场景的图像数据和雷达数据。 处理器（511）还被配置为响应于用户的预期路径中的对象的检测和定位来执行用户可感知的动作。
-
公开(公告)号：WO2007037797A2
公开(公告)日：2007-04-05
申请号：PCT/US2006/031227
申请日：2006-08-09
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： GRAF, Hans, Peter , DURDANOVIC, Igor , COSATTO, Eric , VAPNIK, Vladimir
IPC: G06N3/02
CPC classification number: G06K9/6269 , G06N99/005
Abstract: Disclosed is a parallel support vector machine technique for solving problems with a large set of training data where the kernel computation, as well as the kernel cache and the training data, are spread over a number of distributed machines or processors. A plurality of processing nodes are used to train a support vector machine based on a set of training data. Each of the processing nodes selects a local working set of training data based on data local to the processing node, for example a local subset of gradients. Each node transmits selected data related to the working set (e.g., gradients having a maximum value) and receives an identification of a global working set of training data. The processing node optimizes the global working set of training data and updates a portion of the gradients of the global working set of training data. The updating of a portion of the gradients may include generating a portion of a kernel matrix. These steps are repeated until a convergence condition is met. Each of the local processing nodes may store all, or only a portion of, the training data. While the steps of optimizing the global working set of training data, and updating a portion of the gradients of the global working set, are performed in each of the local processing nodes, the function of generating a global working set of training data is performed in a centralized fashion based on the selected data (e.g., gradients of the local working set) received from the individual processing nodes.
Abstract translation: 公开了一种用于解决大量训练数据的问题的并行支持向量机技术，其中内核计算以及内核高速缓存和训练数据分布在多个分布式机器或处理器上。 多个处理节点用于基于一组训练数据训练支持向量机。 每个处理节点基于处理节点本地的数据，例如梯度的本地子集，选择训练数据的本地工作集。 每个节点发送与工作集有关的所选数据（例如，具有最大值的梯度）并且接收训练数据的全局工作集合的标识。 处理节点优化训练数据的全局工作集，并更新全局训练数据工作集的一部分梯度。 梯度的一部分的更新可以包括生成内核矩阵的一部分。 重复这些步骤直到满足收敛条件。 每个本地处理节点可以存储训练数据的全部或仅一部分。 虽然在每个本地处理节点中执行优化训练数据的全局工作集和更新全局工作集的一部分梯度的步骤，但是在每个本地处理节点中执行生成训练数据的全局工作集的功能， 基于从各个处理节点接收的所选数据（例如，本地工作集的梯度）的集中式。
-
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：WO2021096739A1
公开(公告)日：2021-05-20
申请号：PCT/US2020/058857
申请日：2020-11-04
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MIN, Renqiang , ZHU, Yizhe , KADAV, Asim , GRAF, Hans, Peter
Abstract: A computer-implemented method is provided for disentangled data generation. The method includes accessing (410), by a variational autoencoder, a plurality of supervision signals. The method further includes accessing (420), by the variational autoencoder, a plurality of auxiliary tasks that utilize the supervision signals as reward signals to learn a disentangled representation. The method also includes training (430) the variational autoencoder to disentangle a sequential data input into a time-invariant factor and a time- varying factor using a self-supervised training approach which is based on outputs of the auxiliary tasks obtained by using the supervision signals to accomplish the plurality of auxiliary tasks.
-
公开(公告)号：WO2018052714A3
公开(公告)日：2018-03-22
申请号：PCT/US2017/049327
申请日：2017-08-30
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： MALVIN, Iain , COSATTO, Eric , DURDANOVIC, Igor , GRAF, Hans, Peter
Abstract: A computer-implemented method and system are provided. The system includes an image capture device (510) configured to capture image data relative to an ambient environment of a user. The system further includes a processor (511) configured to detect and localize objects, in a real-world map space, from the image data using a trainable object localization Convolutional Neural Network (CNN). The CNN is trained to detect and localize the objects from image and radar pairs that include the image data and radar data for different scenes of a natural environment. The processor (511) is further configured to perform a user-perceptible action responsive to a detection and a localization of an object in an intended path of the user.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.021 seconds)
