Abstract: An online system and method includes receiving a search query including at least one search term, the search query being associated with a member of the online system. A data tag is separately applied to each individual search term of the search query. An ambiguity status of the search query is determined based on at least some actions as stored in an electronic data storage, also configured to store content items of the online system, including member profile data. A probability distribution of content item categories is determined based on the data tags and at least some of the actions and, if the search is ambiguous, member profile data. At least one content item associated with a content item category having a highest probability on the probability distribution and a user interface displays the at least one content item.

Abstract: Techniques for providing a personalized neural query auto-completion pipeline are disclosed herein. In some embodiments, a computer system, in response to detecting user-entered text that has been entered by a user in a search field of a search engine, generates auto-completion candidates based on the user-entered text and a corresponding frequency level for each one of the auto-completion candidates, ranks the auto-completion candidates based on profile data of the user using a neural network model, and causes at least a portion of the plurality of auto-completion candidates to be displayed in an auto-complete user interface element of the search field within the user interface of the computing device of the user based on the ranking prior to the user-entered text being submitted by the user as part of a search query.

Abstract: In an example embodiment, a warm-start training solution is used to dramatically reduce the computational resources needed to train when retraining a generalized additive mixed-effect (GAME) model. The problem of retraining time is particularly applicable to GAME models, since these models take much longer to train as the data grows. In the past, the strategy to reduce computational resources during retraining was to use less training data, but this affects the model quality, especially for GAME models, which rely on fine-grained sub-models at, for example, member or item levels. The present solution addresses the computational resources issues without sacrificing GAME model accuracy.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for generating personalized smart responses. A messaging system receives a message transmitted as part of a communication session between a first user and a second user and determines a set of candidate responses for replying to the message. The messaging system filters the set of candidate responses based on a personalized vocabulary for the first user, yielding a set of personalized candidate responses. The personalized vocabulary for the first user is determined based on member profile data associated with the first user. The messaging system determines, based on a set of personalized candidate selection rules, a subset of the candidate responses, yielding a set of recommended responses to the message, and causes the set of recommended responses to be presented on the second client device.

Abstract: In an example embodiment, knowledge discovery using deep learning is combined with the scalability and personalization capabilities of generalized additive mixed effect (GAME) modeling. Specifically, features learned in a last fully connected layer of a deep learning model may be used to augment features used in a fixed or random effects training portion of a GAME model.

Abstract: Techniques for predicting sequential data using generative adversarial networks are disclosed herein. In some embodiments, a method comprises: receiving a request associated with a user of an online service; in response to the receiving of the request, retrieving a first plurality of sequential data points of the user from a profile of the user stored on a database of the online service, the first plurality of sequential data points comprising at least one attribute for each one of a plurality of sequential career points of the user; generating at least one predicted data point for the user based on the first plurality of sequential data points using a generative model, the generated at least one predicted data point comprising at least one attribute for a predicted career point for the user; and performing a function of the online service using the generated at least one predicted data point.

Abstract: Relational clustering has attracted more and more attention due to its phenomenal impact in various important applications which involve multi-type interrelated data objects, such as Web mining, search marketing, bioinformatics, citation analysis, and epidemiology. A probabilistic model is presented for relational clustering, which also provides a principal framework to unify various important clustering tasks including traditional attributes-based clustering, semi-supervised clustering, co-clustering and graph clustering. The model seeks to identify cluster structures for each type of data objects and interaction patterns between different types of objects. Under this model, parametric hard and soft relational clustering algorithms are provided under a large number of exponential family distributions.

Abstract: A dome-shaped push switch includes a sheet and a conducting layer disposed at a low surface of the sheet. The sheet has a pressing portion arching upward. The conducting layer is disposed at a lower surface of the sheet. The conductivity of the sheet is greater than that of the sheet. The pressing portion includes at least one through hole penetrating through the pressing portion. The through hole has a side wall, the side wall sequentially has a shear surface and a tear surface from bottom up, and a fillet is provided between the shear surface and a lower surface of the pressing portion.

Abstract: A dome-shaped push switch includes a sheet and a conducting layer disposed at a low surface of the sheet. The sheet has a pressing portion arching upward. The conducting layer is disposed at a lower surface of the sheet. The conductivity of the sheet is greater than that of the sheet. The pressing portion includes at least one through hole penetrating through the pressing portion. The through hole has a side wall, the side wall sequentially has a shear surface and a tear surface from bottom up, and a fillet is provided between the shear surface and a lower surface of the pressing portion.

Abstract: This invention discloses an elliptical exercise apparatus that is characterized in having left and right tracks disposed in a guider frame which is pivotally coupled to a rear portion of the elliptical exercise apparatus. When a user uses the elliptical exercise apparatus, the guider frame is at a use position. When the user folds the elliptical exercise apparatus, the guider frame is at a storage position. A user can complete folding procedure merely by operating the guider frame without lifting some heavy components of the elliptical exercise apparatus.

Abstract: This invention discloses an elliptical exercise apparatus that is characterized in having left and right tracks disposed in a guider frame which is pivotally coupled to a rear portion of the elliptical exercise apparatus. When a user uses the elliptical exercise apparatus, the guider frame is at a use position. When the user folds the elliptical exercise apparatus, the guider frame is at a storage position. A user can complete folding procedure merely by operating the guider frame without lifting some heavy components of the elliptical exercise apparatus.

Abstract: One particular embodiment clusters a plurality of documents using one or more clustering algorithms to obtain one or more first sets of clusters, wherein: each first set of clusters results from clustering the documents using one of the clustering algorithms; and with respect to each first set of clusters, each of the documents belongs to one of the clusters from the first set of clusters; accesses a search query; identifies a search result in response to the search query, wherein the search result comprises two or more of the documents; and clusters the search result to obtain a second set of clusters, wherein each document of the search result belongs to one of the clusters from the second set of clusters.

Abstract: Relational clustering has attracted more and more attention due to its phenomenal impact in various important applications which involve multi-type interrelated data objects, such as Web mining, search marketing, bioinformatics, citation analysis, and epidemiology. A probabilistic model is presented for relational clustering, which also provides a principal framework to unify various important clustering tasks including traditional attributes-based clustering, semi-supervised clustering, co-clustering and graph clustering. The model seeks to identify cluster structures for each type of data objects and interaction patterns between different types of objects. Under this model, parametric hard and soft relational clustering algorithms are provided under a large number of exponential family distributions.

Abstract: This invention discloses an elliptical exercise apparatus that is characterized in having left and right tracks disposed in a guider frame which is pivotally coupled to a rear portion of the elliptical exercise apparatus. When a user uses the elliptical exercise apparatus, the guider frame is at a use position. When the user folds the elliptical exercise apparatus, the guider frame is at a storage position. A user can complete folding procedure merely by operating the guider frame without lifting some heavy components of the elliptical exercise apparatus.

Abstract: One particular embodiment clusters a plurality of documents using one or more clustering algorithms to obtain one or more first sets of clusters, wherein: each first set of clusters results from clustering the documents using one of the clustering algorithms; and with respect to each first set of clusters, each of the documents belongs to one of the clusters from the first set of clusters; accesses a search query; identifies a search result in response to the search query, wherein the search result comprises two or more of the documents; and clusters the search result to obtain a second set of clusters, wherein each document of the search result belongs to one of the clusters from the second set of clusters.

Abstract: A ball joint includes a ball member, a socket member, and a resilient pressing mechanism. The ball member couples with the socket member. The resilient pressing mechanism is positioned between the ball member and the socket member, applying compression to cause the ball member to tightly contact the socket member. The resilient pressing mechanism includes a plurality of springs positioned in parallel between the ball member and the socket member.

Abstract: Relational clustering has attracted more and more attention due to its phenomenal impact in various important applications which involve multi-type interrelated data objects, such as Web mining, search marketing, bioinformatics, citation analysis, and epidemiology. A probabilistic model is presented for relational clustering, which also provides a principal framework to unify various important clustering tasks including traditional attributes-based clustering, semi-supervised clustering, co-clustering and graph clustering. The model seeks to identify cluster structures for each type of data objects and interaction patterns between different types of objects. Under this model, parametric hard and soft relational clustering algorithms are provided under a large number of exponential family distributions.

Abstract: A method for identifying facial features comprises following steps: An image tracing step is performed to receive video data of a plurality of face images and to obtain a real-time background image from the video data by a video tracing technique. A data calculating step is performed to calculate a video data difference between a current face image and the real-time background image. A process setting step is performed to set an iteration number according to the video data difference. A coordinate requesting step is performed to obtain facial feature coordinates of a previous face image, the previous one of the current face image, serving as initial facial feature coordinates. A localization step is performed to obtain current facial feature coordinates of the current image by conducting an iterative calculation according to the iteration number and based on the initial facial feature coordinates.