-
公开(公告)号：US10402752B2
公开(公告)日：2019-09-03
申请号：US15356494
申请日：2016-11-18
Applicant: Facebook, Inc.
Inventor： Marc Aurelio Ranzato , Sumit Chopra , Michael Auli , Wojciech Zaremba
Abstract: A system for training a model to predict a sequence (e.g. a sequence of words) given a context is disclosed. A model can be trained to make these predictions using a combination of individual predictions compared to base truth and sequences of predictions based on previous predictions, where the resulting sequence is compared to the base truth sequence. In particular, the model can initially use the individual predictions to train the model. The model can then be further trained over the training data in multiple iterations, where each iteration includes two processes for each training element. In the first process, an initial part of the sequence is predicted, and the model and model parameters are updated after each prediction. In the second process, the entire remaining amount of the sequence is predicted and compared to the corresponding training sequence to adjust model parameters to encourage or discourage each prediction.
-
公开(公告)号：US10402495B1
公开(公告)日：2019-09-03
申请号：US15694031
申请日：2017-09-01
Applicant: Facebook, Inc.
Inventor： Alexander Matthew Rush , Sumit Chopra , Jason Edward Weston
IPC: G06F17/27 , G10L25/30 , G10L15/197
Abstract: In one embodiment, a sequence of input words is received. Each of the input words is encoded as an indicator vector, wherein a sequence of the indicator vectors captures features of the sequence of input words. The sequence of the indicator vectors is then mapped to a distribution of a contextual probability of a first output word in a sequence of output words. For each subsequent output word, the sequence of the indicator vectors is encoded with a context, wherein the context comprises a previously mapped contextual probability distribution of a fixed window of previous output words; and the encoded sequence of the indicator vectors and the context is mapped to the distribution of the contextual probability of the subsequent output word. Finally, a condensed summary is generated using a decoder by maximizing the contextual probability of each of the output words.
-
公开(公告)号：US20170061294A1
公开(公告)日：2017-03-02
申请号：US14949436
申请日：2015-11-23
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Keith Adams , Sumit Chopra
CPC classification number: G06F16/334 , G06F16/3331 , G06N3/0454
Abstract: In one embodiment, a method includes receiving text query that includes n-grams. A vector representation of each n-gram is determined using a deep-learning model. A nonlinear combination of the vector representations of the n-grams is determined, and an embedding of the text query is determined based on the nonlinear combination. The embedding of the text query corresponds to a point in an embedding space, and the embedding space includes a plurality of points corresponding to a plurality of label embeddings. Each label embedding is based on a vector representation of a respective label determined using the deep-learning model. Label embeddings are identified as being relevant to the text query by applying a search algorithm to the embedding space. Points corresponding to the identified label embeddings are within a threshold distance of the point corresponding to the embedding of the text query in the embedding space.
Abstract translation: 在一个实施例中，一种方法包括接收包括n-gram的文本查询。 使用深度学习模型确定每个n-gram的向量表示。 确定n-gram的矢量表示的非线性组合，并且基于非线性组合来确定文本查询的嵌入。 文本查询的嵌入对应于嵌入空间中的一个点，并且嵌入空间包括与多个标签嵌入相对应的多个点。 每个标签嵌入基于使用深度学习模型确定的相应标签的向量表示。 通过将搜索算法应用于嵌入空间，标签嵌入被标识为与文本查询相关。 与识别的标签嵌入相对应的点在与嵌入空间中的文本查询的嵌入相对应的点的阈值距离内。
-
4.发明申请SYSTEMS AND METHODS FOR DETERMINING VIDEO FEATURE DESCRIPTORS BASED ON CONVOLUTIONAL NEURAL NETWORKS 有权基于连续神经网络确定视频特征描述符的系统和方法公开(公告)号：US20160189009A1
公开(公告)日：2016-06-30
申请号：US14585826
申请日：2014-12-30
Applicant: Facebook, Inc.
Inventor： Du Le Hong Tran , Balamanohar Paluri , Lubomir Bourdev , Robert D. Fergus , Sumit Chopra
CPC classification number: G06K9/00744 , G06N3/0454 , G06N3/084
Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.
Abstract translation: 系统，方法和非暂时的计算机可读介质可以获取要确定视频特征描述符的视频内容。 可以至少部分地基于包括一组二维卷积层和一组三维卷积层的卷积神经网络来处理视频内容。 可以从卷积神经网络生成一个或多个输出。 可以至少部分地基于来自卷积神经网络的一个或多个输出来确定用于视频内容的多个视频特征描述符。
-
公开(公告)号：US10402750B2
公开(公告)日：2019-09-03
申请号：US14984956
申请日：2015-12-30
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Keith Adams , Sumit Chopra
Abstract: In one embodiment, a method includes accessing a first set of entities, with which a user has interacted, and a second set of entities in a social-networking system. A first set of vector representations of the first set of entities are determined using a deep-learning model. A target entity is selected from the first set of entities, and the vector representation of the target entity is removed from the first set. The remaining vector representations in the first set are combined to determine a vector representation of the user. A second set of vector representations of the second set of entities are determined using the deep-learning model. Similarity scores are computed between the user and each of the target entity and the entities in the second set of entities. Vector representations of entities in the second set of entities are updated based on the similarity scores using the deep-learning model.
-
Patent Agency Ranking
公开(公告)号：US10387464B2
公开(公告)日：2019-08-20
申请号：US14949436
申请日：2015-11-23
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Keith Adams , Sumit Chopra
Abstract: In one embodiment, a method includes receiving text query that includes n-grams. A vector representation of each n-gram is determined using a deep-learning model. A nonlinear combination of the vector representations of the n-grams is determined, and an embedding of the text query is determined based on the nonlinear combination. The embedding of the text query corresponds to a point in an embedding space, and the embedding space includes a plurality of points corresponding to a plurality of label embeddings. Each label embedding is based on a vector representation of a respective label determined using the deep-learning model. Label embeddings are identified as being relevant to the text query by applying a search algorithm to the embedding space. Points corresponding to the identified label embeddings are within a threshold distance of the point corresponding to the embedding of the text query in the embedding space.
-
公开(公告)号：US20190340538A1
公开(公告)日：2019-11-07
申请号：US16512128
申请日：2019-07-15
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Keith Adams , Sumit Chopra
Abstract: In one embodiment, a method includes retrieving a first vector representation of a first entity, with which a user has interacted, and a second vector representation of a second entity, with which the user has not interacted. The first and second vector representations are determined using an initial deep-learning model. A first similarity score is computed between a vector representation of the user and the first vector representation, and a second similarity score is computed between the vector representation of the user and the second vector representation. The second vector representation is updated if the second similarity score is greater than the first similarity score using the initial deep-learning model. An updated deep-learning model is generated based on the initial deep-learning model and on the updated second vector representation.
-
公开(公告)号：US20190332617A1
公开(公告)日：2019-10-31
申请号：US16505521
申请日：2019-07-08
Applicant: Facebook, Inc.
Inventor： Jason E. Weston , Keith Adams , Sumit Chopra
Abstract: In one embodiment, a method includes receiving, from a client system, a text input comprising one or more n-grams, determining, using a deep-learning model, a vector representation of the text input based on the one or more n-grams, determining an embedding of the vector representation of the text input in a d-dimensional embedding space, identifying one or more labels based on, for each of the one or more labels, a respective similarity of an embedding of a vector representation of the label in the embedding space to the embedding of the vector representation of the text input, and sending, to the client system in response to the received text input, instructions for presenting a user interface comprising one or more of the identified labels as suggested labels.
-
9.发明授权公开(公告)号：US10198637B2
公开(公告)日：2019-02-05
申请号：US15848891
申请日：2017-12-20
Applicant: Facebook, Inc.
Inventor： Du Le Hong Tran , Balamanohar Paluri , Lubomir Bourdev , Robert D. Fergus , Sumit Chopra
Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.
-
公开(公告)号：US20180144264A1
公开(公告)日：2018-05-24
申请号：US15356494
申请日：2016-11-18
Applicant: Facebook, Inc.
Inventor： Marc Aurelio Ranzato , Sumit Chopra , Michael Auli , Wojciech Zaremba
CPC classification number: G06N20/00 , G06F17/277 , G06F17/2785 , G06N3/0472 , G06N3/084
Abstract: A system for training a model to predict a sequence (e.g. a sequence of words) given a context is disclosed. A model can be trained to make these predictions using a combination of individual predictions compared to base truth and sequences of predictions based on previous predictions, where the resulting sequence is compared to the base truth sequence. In particular, the model can initially use the individual predictions to train the model. The model can then be further trained over the training data in multiple iterations, where each iteration includes two processes for each training element. In the first process, an initial part of the sequence is predicted, and the model and model parameters are updated after each prediction. In the second process, the entire remaining amount of the sequence is predicted and compared to the corresponding training sequence to adjust model parameters to encourage or discourage each prediction.
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.017 seconds)
