Abstract: A neural network structure is separated into an odd neural network including only the odd layers and an even neural network including only the even layers. In order to allow for parallel execution, for forward propagation a second input is generated from the original input, while for backward propagation a second error gradient is generated. Parallel execution may accelerate the forward and backward propagation operations without significant change in accuracy of the model. Additionally, restructuring a single neural network into two or more parallel neural networks may reduce the total time needed for training.

Abstract: An audio visual haptic signal reconstruction method includes first utilizing a large-scale audio-visual database stored in a central cloud to learn knowledge, and transferring same to an edge node; then combining, by means of the edge node, a received audio-visual signal with knowledge in the central cloud, and fully mining semantic correlation and consistency between modals; and finally fusing the semantic features of the obtained audio and video signals and inputting the semantic features to a haptic generation network, thereby realizing the reconstruction of the haptic signal. The method effectively solves the problems that the number of audio and video signals of a multi-modal dataset is insufficient, and semantic tags cannot be added to all the audio-visual signals in a training dataset by means of manual annotation. Also, the semantic association between heterogeneous data of different modals are better mined, and the heterogeneity gap between modals are eliminated.

Abstract: Described herein is a method, system, and non-transitory computer readable medium for preventing data loss from both producer and consumer systems in continuous availability event-driven applications. The process for preventing data loss may replicate events at the broker level, and selectively receive replica events at the consumer level to account for the case the originally sent event is not received, while conserving computer and network resources. Alternatively, events and replica events may be received in duplicate. In either mode of reception, machine-learning may be used for implementing algorithms which further help to conserve resources and aid in preventing further data loss.

Abstract: Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of receiving, from an extraction, transform, load (ETL) application, a matrix, which can comprise raw feature data; storing the matrix comprising the raw feature data in a standard format in the one or more non-transitory computer readable storage devices; receiving a configuration file over a computer network; storing the configuration file in a standard format in the one or more non-transitory computer readable storage devices; instantiating one or more unifier applications based upon the configuration file; identifying relevant feature data of the raw feature data; storing the relevant feature data in a standardized format in an output file in the one or more non-transitory computer-readable storage devices; and transmitting, over the computer network in real time to a model building system, the output file compri

Abstract: Systems and methods are provided for using an algorithm and data structure for efficient and accurate classification of data items into recovery classes. When a target recovery time (TRT) is specified for a data set, a system may obtain version metadata regarding data items in the data set. The metadata may be obtained in reverse chronological order such that the latest record representing a version or other storage operation is first, followed by the second latest record, and so on. The system may use a bidirectional doubly linked list to efficiently store version data for a particular data item in memory. As version metadata records are read and added to the data structure in reverse chronological order, classification determinations may be triggered when certain conditions are met.

Abstract: Systems and methods are described herein for detecting that a person of interest is displayed in a live video for a threshold amount of time, attempting to identify an identity of the person determining that the attempting has failed, identifying broadcast times corresponding to a period of time in which the person was displayed in the live video, identifying trending topics in a social media space that relate to the live video, ascertaining an identity of the person of interest based on the trending topics, comparing the identity of the person of interest to a database of social media profiles, identifying a social media component that corresponds to the person, determining whether the person has modified the social media component within a predefined period of time, and providing information relating to a modification of the social media component simultaneously with the video.

Abstract: Methods and systems to identify video content based on video fingerprint matching are described. In some example embodiments, the methods and systems generate a query fingerprint of a frame of video content captured at a client device, query a database of reference fingerprints, determine the query fingerprint of the frame of captured video content matches a reference fingerprint, and identify the video content based on the match of fingerprints.

Abstract: A system for extracting key phrase candidates from a corpus of documents, including a processor, a memory, and a program executing on the processor. The system is configured to run a key phrase model to extract one or more key phrase candidates from each document in the corpus and convert each extracted key phrase candidate into a feature vector. The key phrase model also filters the feature vectors to remove duplicates using a classifier that was trained on a set of key phrase pairs with manual labels indicating whether two key phrases are duplicates of each other, to produce remaining key phrase candidates. The system uses the remaining key phrase candidates in a computer-implemented application.

Abstract: Herein are techniques that train regressor(s) to predict how effective would a machine learning model (MLM) be if trained with new hyperparameters and/or dataset. In an embodiment, for each training dataset, a computer derives, from the dataset, values for dataset metafeatures. The computer performs, for each hyperparameters configuration (HC) of a MLM, including landmark HCs: configuring the MLM based on the HC, training the MLM based on the dataset, and obtaining an empirical quality score that indicates how effective was said training the MLM when configured with the HC. A performance tuple is generated that contains: the HC, the values for the dataset metafeatures, the empirical quality score and, for each landmark configuration, the empirical quality score of the landmark configuration and/or the landmark configuration itself. Based on the performance tuples, a regressor is trained to predict an estimated quality score based on a given dataset and a given HC.

Abstract: A method begins by a computing device of a storage network receiving a data access request of a transaction regarding a data segment, where at least one data segment is dispersed storage error encoded into a set of encoded data slices that are stored in a set of storage units of the storage network. The method continues by executing the data access request. The method continues by generating a set of audit record data files regarding the execution of the data access request, where an audit record data file includes a source identifier, a target identifier, a unique identifier associated with the data segment, a timestamp, and a type code that indicates a type of storage network activity associated with the transaction. The method continues by storing the set of audit record data files in the storage network.

Abstract: In some embodiments, an instance of a distributed database can be configured at a first compute device within a set of compute devices that implements the distributed database via a network. A database convergence module can define a first event linked to a first set of events and receive, from a second compute device from the set of compute devices, a second event (1) defined by the second compute device and (2) linked to a second set of events. The database convergence module can define a third event linked to the first event and the second event. The database convergence module can identify an order associated with a third set of events based at least on the first set of events and the second set of events, and store in the instance of the distributed database the order associated with the third set of events.

Abstract: Embodiments of the present application disclose a file directory traversal method, apparatus, device, and medium, and relate to the field of file system processing technology and cloud computing. The method may include: receiving a current directory traversal request of a terminal for a target directory; determining a directory calling identifier of the terminal by parsing the current directory traversal request; wherein, the directory calling identifier is used for uniquely representing the terminal under the target directory; determining a directory entry currently requested to be called by the terminal under the target directory, according to the current directory traversal request; and sending the determined directory entry to the terminal in accordance with the directory calling identifier.

Abstract: Various embodiments are directed to managing annotations over a network for visualizations. An annotation engine enables users to associate a data object value with any number of notes, comments, videos, graphics, pictures, audio, references, links, or any other information A visualization engine generates visualizations that include annotation identifiers when the visualizations include data object values that are associated with annotations and the type of visualization is approved for use with the annotations.

Abstract: A spatial indexing system receives a set of walkthrough videos of an environment taken over a period of time and receives an image search query that includes an image of an object. The spatial indexing system searches the set of walkthrough videos for instances of the object. The spatial indexing system presents search results in a user interface, displaying in a first portion a 2D map associated with one walkthrough video with marked locations of instances of the object and a second portion with a histogram of instances of the object over time in the set of walkthrough videos.

Abstract: In various example embodiments, a system, computer readable medium and method for schema update engine dynamically updating a target data storage system. Incoming data records are received. A front-end schema of the incoming data records is identified. The front-end schema and the current target schema are compared. Based on identifying a difference between the front-end schema and the current target schema, the current target schema is updated in order to be identical to the front-end schema. The current target data file is closed and the incoming data records are stored in a new target data file according to the updated target schema.

Abstract: In some embodiments, an apparatus includes an instance of a distributed database at a first compute device configured to be included within a set of compute devices that implement the distributed database. The apparatus also includes a processor configured to define a first event linked to a first set of events. The processor is configured to receive, from a second compute device from the set of compute devices, a signal representing a second event (1) defined by the second compute device and (2) linked to a second set of events. The processor is configured to identify an order associated with a third set of events based at least one a result of a protocol. The processor is configured to store in the instance of the distributed database the order associated with the third set of events.

Abstract: Some embodiments provide a non-transitory machine-readable medium stores a program. The program receives a query for data that includes an intersection operation on a first set of strings and a second set of strings. The program further generates a plurality of candidate query execution plans based on the query. The program also determines a plurality of execution costs associated with the plurality of candidate query execution plans. The program further selects a query execution plan from the plurality of candidate query execution plans based on the plurality of execution costs. The program also executes the query execution plan to generate a set of query results for the query.

Abstract: Facilitating exclusive local locks on a distributed file system is provided herein. An embodiment relates to a node device of a cluster of node devices. The node device can comprise a processor and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations. The operations can comprise determining at least one resource is to be removed from a cache of the node device. The operations also can comprise implementing an exclusive local lock over a defined lock. The defined lock can indicate interest in the at least one resource by other node devices of the cluster of node devices other than the node device. Further, the operations can comprise removing the at least one resource from the cache. The other node devices are not notified of the removing.

Abstract: A bottom-up hierarchical computer network architecture is provided. The architecture may include a central server. The architecture may also include a plurality of edge nodes that may be coupled to the central server. At least a first one of the edge nodes may be configured to process a transaction, compile data associated with the transaction, and store the data as a master dataset in the first edge node. The architecture may also include a data administration module. The data administration module may be configured to compare the master dataset in the first edge node to transactional data in the central server. When the transactional data in the central server is inconsistent with the master dataset in the first edge node, the data administration module may be configured to update the transactional data in the central server to be consistent with the master dataset in the first edge node.

Abstract: A device searches a file being recorded that includes lines sorted in accordance with keys included in the lines to find a line that matches a pattern. When the device receives a pattern, it initializes upper and lower limits of a search range and calculates a middle position between the limits. It acquires, from the file, a middle line that starts at or before the middle position and ends after it. If the key included in the middle line matches the pattern, it outputs the middle line and re-sets the upper or lower limit based on whether the key included in the middle line is greater or less than the pattern and, if there is a distance greater than a length of a newline between the limits, repeats the procedure starting from the middle position. Otherwise, it outputs a result to the effect that no matching line has been found.