Abstract: Techniques are disclosed relating to training a neural network using private training data. In some embodiments, a central computing system is configured to maintain an at least partially trained neural network and information that specifies data formats for inputs to the model and outputs from the model. In some embodiments, partner computing systems maintain subsections of the neural network model and may train them using data that is not shared with other partner computing systems or the central computing system. Parameters resulting from the training may be transmitted to the central computing system. In some embodiments, the central computing system processes the parameters to generate the updated complete version of the neural network model and transmits parameters from the updated complete version of the model to the partner computing systems. The partner computing systems may use the updated complete model to detect anomalies in input data.

Abstract: Provided is a process, including: obtaining a set of candidate captions associated with one or more data visualizations; obtaining criteria designating whether candidate captions are descriptive of potential instances of the one or more data visualizations; producing a plurality of simulated instances of each of the one or more data visualizations; determining which of the captions apply to each of the simulated instances of each of the one or more data visualizations based on whether the simulated instances satisfy corresponding criteria; causing captions determined to be applicable to be presented; receiving feedback indicative of whether presented captions are perceived as descriptive of the corresponding simulated instances of data visualizations; and adjusting the criteria based on the feedback.

Abstract: Provided is a process, including: obtaining, with one or more processors, data to be summarized, wherein the data comprises a plurality of metrics; generating, with one or more processors, a plurality of instances of data visualizations depicting at least some of the data by systematically varying: type of data visualization, and mapping of fields of the data to data visualizations; generating, with one or more processors, with a trained captioning model, intermediate natural language text summaries of each of the instances of data visualizations; summarizing, with one or more processors, with a natural language text summarization model, the intermediate natural language text summaries to form a natural language text description of the data; and storing, with one or more processors, the natural language text description of the data in memory.

Abstract: Provided is a process, including: obtaining a first identifier of a first user for whom a first presentation including a first natural language text summary of data is to be provided; selecting a first domain from among a plurality of domains based on the first identifier; selecting a first set of fields among a plurality of fields of the data based on the first domain; determining a first set of exposure-control rules based on the first set of fields of data; determining a first applicable subset of the first set exposure-control rules by comparing criteria of the first set of exposure-control rules to user attributes associated with the first identifier; generating with a trained captioning model, the first natural language text summary in the first domain of the data compliant with exposure permissions of the first applicable subset of the first set of exposure-control rules.

Abstract: Provided is a process, including: receiving a command corresponding to user input to an interactive dashboard application from a user; producing in response to the command, instances of data visualizations depicting data to be visualized; generating, with a trained captioning model, one or more narrative captions determined to be descriptive of the produced instances of data visualizations, wherein the one or more narrative captions include a natural language description of a phenomenon exhibited, at least in part, by the data to be visualized and visually depicted in at least one of the produced instances of data visualizations; and causing the one or more narrative captions to be presented to the user.

Abstract: A server computer system stores a plurality of display generation objects executable to cause display of display images. The server computer system receives a camera image from a user device. The server computer system determines that a particular display image included in the camera image corresponds to a particular display generation object. The server computer system then subscribes the user device to one or more data feeds selected based on the particular display generation object, and sends one or more notifications corresponding to the one or more selected data feeds to the user device.

Abstract: A fork in a block chain data structure is identified, the block chain data structure including a first set of blocks each describing a respective transaction. The fork includes a first branch beginning with a first block and a second branch beginning with a different second block. The first branch includes a first set of blocks comprising at least the first block, and the second branch includes a second set of blocks including at least the second block. A determination is made, based on a consensus protocol, that the second branch is to be discarded. Accordingly, a meta block is generated to identify and describe the second branch. The meta block is to be included in a meta block chain data structure. The meta block chain data structure is separate from the block chain data structure and comprises meta blocks to record orphan branches of the block chain data structure.

Abstract: Techniques are disclosed relating to a computer system detecting the start of a meeting between a plurality of individuals, initiating a recording of the particular meeting, receiving a recording confirmation command from one of the plurality of individuals, and based on receiving the recording confirmation command causing the recording of the particular meeting to be retained by the computer system for subsequent playback. The recording confirmation command may be received during the meeting as it is being recorded or after the meeting has ended. The computer system may store meeting metadata indicative of the recorded meeting. In some embodiments, the meeting metadata is stored in a blockchain-based shared ledger.

Abstract: Techniques are disclosed relating to serving an electronic search warrant. In some embodiments, a computer system accesses a blockchain including an electronic warrant that authorizes access to a controlled device having confidential data. The computer system sends a request for the confidential data to the controlled device, the request identifying the electronic warrant. The computer system receives the confidential data from the controlled device and appends a first record to a second record in blockchain. The first record includes the confidential data, a first digital signature generated from the contents of the first record, and a second digital signature obtained from the second record. In some embodiments, the computer system sends a request for the electronic warrant to a second computer system associated with a court. The request identifies a public key for inclusion in the electronic warrant and having a private key to generate the first digital signature.

Abstract: An apparatus includes a sensor circuit and a wireless communication interface. The sensor circuit may periodically sense a value for a particular environmental variable. The wireless communication interface may update a dynamic address for the apparatus based on the periodically sensed value, and receive a query from a base station. The query may include a conditional address corresponding to the particular environmental variable. In response to a first comparison of the conditional address to a current dynamic address, the wireless communication interface may send a reply to the base station indicating whether the query has matched for the apparatus. The reply to the query may be performed without requesting a reading of the particular environmental variable from the sensor circuit.

Abstract: Techniques are disclosed relating to a computer system receiving recordings of meetings between individuals, encrypting the recording, storing the encrypted recording, and determining whether to decrypt the encrypted recording based on decryption information indicative of ones of the individuals have assented to the decryption of the encrypted recording and a cryptographic policy. The computer system may also perform semantic analysis of the audio of the meeting to identify decision statements made at the meeting and factor statements made at the meeting upon which the decision statement is based. The computer system may also store meeting metadata associated with the meeting that is indicative of the decision statement and factor statements.

Abstract: A fork in a block chain data structure is identified, the block chain data structure including a first set of blocks each describing a respective transaction. The fork includes a first branch beginning with a first block and a second branch beginning with a different second block. The first branch includes a first set of blocks comprising at least the first block, and the second branch includes a second set of blocks including at least the second block. A determination is made, based on a consensus protocol, that the second branch is to be discarded. Accordingly, a meta block is generated to identify and describe the second branch. The meta block is to be included in a meta block chain data structure. The meta block chain data structure is separate from the block chain data structure and comprises meta blocks to record orphan branches of the block chain data structure.

Abstract: Provided is a process of conducting a collaborative session between two analytics graphical user interfaces (GUI), the process including: instructing a first computing device associated with a first user to display a first GUI having a first graph depicting a first set of values of a first metric; determining that the first graph is to be shared on a second computing device associated with a second user in a second GUI; inferring that the second user prefers to view the first metric in a second graph based on a record of previous interactions in which the second graph was selected to view the first metric; and in response, instructing the second computing device to display in the second GUI the second graph depicting at least some of the first set of values of the first metric.

Abstract: Aspects of the embodiments are directed to a real-time robot command and control interface. An aspect of the interface allows a user to select objects from an image of a scene and to reposition the objects within the scene. Another aspect of the interface can process the image data to determine one or more commands for instructing a robot to move the object to a desired location. The interface can use image and pattern recognition algorithms to determine the new location of the object and can use control algorithms to instruct the robot to move the object.

Abstract: Technologies are provided in embodiments to detect anomalies by shadowing human-computer interaction channels. Embodiments include accessing a shadow signal generated by a shadowing device. In an embodiment, the shadow signal can be a video input stream of display screen images rendered on a display screen, where the display screen images were recorded by the shadowing device. The embodiment also includes identifying, at the shadowing device, a first frame of the video input stream, and determining whether an anomaly is associated with the video input stream based, at least in part, on applying a rule of a set of rules to at least a portion of the first frame, where the set of rules defines a control image associated with the video input stream. The embodiment further includes determining whether to take an action based on the determining whether the anomaly is associated with the video input stream.

Abstract: Techniques are disclosed relating to determining a physical location of an item within an environment. For example, in various embodiments, a location system may determine a location of a first item of a plurality of items. In some embodiments, the location system may emit a pulse of light via a light source. The location system may receive a plurality of reflections that have been reflected from retroreflective material on one or more of the plurality of items. Further, in some embodiments, the location system may determine a direction of the location of the first item relative to a reference location. The location system may, in some embodiments, determine a distance between the reference location and the first item. Additionally, in some embodiments, the location system may determine identification information associated with the first item.

Abstract: Techniques are disclosed relating to configuring a neural network based on information received via a dashboard user interface. In some embodiments, a computing system displays a dashboard that includes a set of plots for displaying data and user interface elements that may be used to configure the number and type of the plots. The plots may display information of various kinds, including raw or processed data, relationships between data, processes applied to data, etc. and may be different types, including, e.g., spark lines, scatter, or time series, etc. The dashboard module is operable to communicate the user input to a module operable to generate a neural network topology. User input to the dashboard may provide information regarding sources of data to be used for generating plots, or training or running the neural network. Results based on processing data using the trained neural network may be displayed on the dashboard.

Abstract: Techniques are disclosed relating to training a neural network using private training data. In some embodiments, a central computing system is configured to maintain an at least partially trained neural network and information that specifies data formats for inputs to the model and outputs from the model. In some embodiments, partner computing systems maintain subsections of the neural network model and may train them using data that is not shared with other partner computing systems or the central computing system. Parameters resulting from the training may be transmitted to the central computing system. In some embodiments, the central computing system processes the parameters to generate the updated complete version of the neural network model and transmits parameters from the updated complete version of the model to the partner computing systems. The partner computing systems may use the updated complete model to detect anomalies in input data.

Abstract: Techniques are disclosed relating to detecting computing operations using thermal sensing. In some embodiments, a first computer system may analyze a series of thermal images of a target computer system. In some embodiments, the first computer system may identify, based on the analyzing, a first thermal image pattern from the series of thermal images of the first target computer system. In some embodiments, the first computer system may compare the first thermal image pattern to known thermal image patterns indicative of known computing operations. In some embodiments, the first computer system may provide an output indicative of the comparing.

Abstract: Systems and methods may include receiving data of a physical system. The systems and methods may include determining whether an anomalous event has occurred based on the data. The systems and methods may include, in response to determining that the anomalous event has occurred, capturing data of the physical system and of an environment. The systems and methods may include generating a virtual representation of the physical system and the environment based on the captured data. The systems and methods may include repeatedly simulating data of the virtual representation by varying parameters of the captured data. The systems and methods may include determining which parameters are a root cause of the anomalous event based on the simulated performance data. The systems and methods may include determining particular values of the parameters that are likely the root cause of the anomalous event to use as a trigger for a proactive process.