Abstract: Data analysis and neural network training technology includes generates, based on a sparse neural network, a feature selection ranking representing a ranked list of features from input data, where the sparse neural network is a shallow neural network trained with the input data and then pruned, generates, based on the sparse neural network, a feature set dictionary representing interactions among features from the input data, and performs, based on the feature selection ranking and the feature set dictionary, one or more of generating an output analysis of insights from the input data and the sparse neural network, or training of a second neural network. The technology can also adjust the input data based on the feature set ranking to produce adjusted input data, where the sparse neural network is re-trained based on the adjusted input data and then pruned prior to generating the feature set dictionary.

Abstract: Aspects of the present disclosure relate to automated document processing systems. In particular, embodiments disclosed herein provide an architecture for seamlessly integrating code representations of electronic documents generated by various different extraction systems into a single document processing system. Certain embodiments provide for generating a code representation of an electronic document based on an entity extracted from the electronic document. The code representation includes an entity representation that comprises an index indicator appended to an identifier for the entity, which may comprise a column of items. Some embodiments provide for applying a transformation to the entity representation to produce an intermediate code representation of the electronic document, wherein the transformation comprises a format for entities or a format for entity representations.

Abstract: A method of applying non-linear regression on a set of data points to get an estimate is described herein. The method includes receiving a set of N datapoints, separating the set of N datapoints into Nb batches, receiving a family of fitting functions, and minimizing a log-cosh cost function for each batch by selecting parameters that minimize the log-cosh cost function. The parameters are obtained by: receiving a matrix product state (MPS) model and training the MPS to minimize loss over all the Nb batches, including choosing an MPS with M+D tensors. All tensors except D correspond to one datapoint in each of the Nb batches, D extra tensors in the MPS have a physical dimension of size M corresponding to the number of possible outputs for a given batch, and the coefficients of the tensors in the MPS minimize the log-cosh cost function sequentially over all the Nb batches.

Abstract: A method for generating self-serve integrations includes receiving a network address of a configuration file that includes parameters to interface with a server. The method extracts, from the configuration file, endpoints and operation(s) available to manipulate each endpoint. The method displays a first table having a rows displaying (a) a given endpoint and (b) a menu for selecting a given operation to manipulate the given endpoint. The method, upon selection of a given row, displays input field(s) that accept a parameter, authorization, header, body, and/or response data. The method gathers, from the server, a data fields available at the given endpoint. The method displays a second table having rows that have data field(s), and input(s) for a data type, column type, a display name, unit, description, primary key, secondary key, and/or an indexing toggle.

Abstract: Devices, systems, methods, and processes for facilitating new application onboarding within a workload protection solution is described herein. As new applications are introduced into a system, users or network administrators may not be knowledgeable on how to properly onboard the application sufficient to effect proper segmentation, monitoring, and the like. Without proper onboarding, the system may not be optimized and can become less optimal over time as new applications are added. By automating at least a portion of that process, a more optimal system can be achieved. This automation may be achieved through a series of prompts to the user to input various characteristics about the application that can be utilized to generate a recommended policy to apply to the application in order to onboard it into the system. The policy can be reviewed, confirmed, and applied through a graphical user interface or the like.

Abstract: Techniques for time-bound hyperparameter tuning are disclosed. The techniques enable the determination of optimized hyperparameters for a machine learning (ML) model given a specified time bound using a three-stage approach. A series of trials are executed, during each of which the ML model is trained using a distinct set of hyperparameters. In the first stage, a small number of trials are executed to initialize the algorithm. In the second and third stages, a certain number of trials are executed in each stage. The number of trials to run in each stage are determined using one or more computer-implemented techniques. The computer-implemented techniques can also be used to narrow the hyperparameter search space and the feature space. Following the third stage, a set of optimized hyperparameters is adopted based a predefined optimization criterion like minimization of an error function.

Abstract: A computing system obtains a first article about a first topic, where the first article references a plurality of entities including a person. The computing system identifies the person as a dominant entity of the first article. The computing system determines whether the first article expresses negative sentiment based upon content of the first article. In accordance with a determination that the first article does not express negative sentiment, the computing system retrieves a uniform resource locator (URL) of a webpage about a second topic that is of interest to the first person. Upon receiving a request for the first article from a computing device, the computing system causes the first article and a link to be concurrently displayed on a display, where the URL of the webpage is embedded in the link.

Abstract: Embodiments described herein relate to systems and methods for automatically generating content, generating API requests and/or request bodies, structuring user-generated content, and/or generating structured content in collaboration platforms, such as documentation systems, issue tracking systems, project management platforms, and other platforms. The systems and methods described use a network architecture that includes a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and/or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.

Abstract: A device including a memory and a processor. The processor receives electronic information. The processor analyzes the electronic information. The processor displays, based on analyzing the electronic information, the electronic information on a graphical user interface. The displayed electronic information is shown as a first electronic formation, and the graphical user interface is controlled by the processor. The device receives an electronic communication and changes the displayed electronic information to a second electronic formation displayed on the graphical user interface. The change from the first electronic formation to the second electronic formation occurs instantaneously.

Abstract: Disclosed embodiments relate to data management of entity pairs. Techniques can include receiving at least two sets of data and a data management task request with each including a set of entities. Techniques can determine a location of each entity in received data sets in a representative space by determining representative structure of the set of entities. Techniques can then for an entity, a set of representative entity pairs from each set of the at least two sets of data based on how close they are in the representative space. Technique can then analyze the set of representative entity pairs to identify most similar entity pairs include in a set of candidate pairs by determining closeness of location of entities in each entity pair in the representative space. Technique can then determine matched entity pairs of the candidate pairs using a first machine learning model is trained using the candidate pairs by applying labels, and utilizing the matched pairs to perform the requested data management task.

Abstract: A method can be performed by a browser. The method can include presenting at least a portion of a resource address; presenting a rendered webpage in a browser content window, the rendered webpage being associated with the resource address; presenting an annotation area, the annotation area being outside the browser content window; receiving, in association with a user account, an annotation in the annotation area; and storing the annotation in association with the user account and the resource address.

Abstract: Machine learning, artificial intelligence, and other computer-implemented methods are used to identify various semantically important chunks in documents, automatically label them with appropriate datatypes and semantic roles, and use this enhanced information to assist authors and to support downstream processes. Chunk locations, datatypes, and semantic roles can often be automatically determined from what is here called “context”, to wit, the combination of their formatting, structure, and content; those of adjacent or nearby content; overall patterns of occurrence in a document, and similarities of all these things across documents (mainly but not exclusively among documents in the same document set).

Abstract: A virtual whiteboard is modified responsive to editing commands. Each of the editing commands results in a respective state of the virtual whiteboard. At least some of the respective states are stored as whiteboard snapshots. A command to display one of the whiteboard snapshots is received. Based on the command, a user interface associated with the virtual whiteboard is updated according to the one of the whiteboard snapshots.

Abstract: The present disclosure relates to systems and methods for automatically identifying additional content for a webpage. The systems and methods may create a side pane placed next to a webpage to supplement the webpage in a browser. The side pane may provide additional information or additional content to help users consume the webpage. The additional content may provide webpage insights and help the users further explore the webpage.

Abstract: Method for learning synaptic weight values of a neural network, related data processing method, computer program, calculator and processing system The invention relates to a method for training synaptic weight values of at least one layer of an artificial neural network. The method is computer-implemented, and comprises training the weight values from training data, each weight value from said training being a quantized weight value belonging to a set of quantized values. The set of quantized values consists of values encoded with a predefined number B of bits, and with a quantization step P between two successive quantized values that satisfies: P = 1 ? 2 B - 1 2 ? where ?·? represents the integer part function; the quantized values also being included in a predefined interval chosen from the interval [?1?P; 1] and the interval [?1; 1].

Abstract: As described herein, a system, method, and computer program are provided for using a dynamic threshold mechanism that is utilizing a set of machine learning models to auto-complete user input fields. User access to a form having a plurality of user input fields is detected. One or more of the plurality of user input fields are auto-completed over a sequence of stages, utilizing at least one machine learning model.

Abstract: A method and a system for remotely controlling interface display, a device, and a storage medium. The method includes steps of: detecting a first operation based on a first display window displayed in a first device, where the first display window displays a display interface of a second device, and the first operation is used to indicate an operation of controlling the second device to perform an occlusion on an area to be occluded in the display interface of the second device; determining area information of the area based on the first operation; and sending an occlusion instruction to the second device based on the area information, where the occlusion instruction is used to instruct the second device to perform an occlusion processing on the area based on the area information.

Abstract: A method and a system include receiving indication of a user interaction within a pre-determined time period, determining that the user interaction is a contextual triggering event based on a plurality of triggering conditions, identifying a media content item associated with the contextual triggering event, generating a first user interface including a user-selectable element representing a content transmission proposal, in response to detecting a user selection of the user-selectable element, generating a second user interface, the second user interface including the media content item and a plurality of user-selectable entity icons.

Abstract: A method, apparatus, electronic device and computer-readable storage medium for task creation. The method includes: in response to a triggering operation of creating a first task for a single file message in a session, determining a first title name of the first task based on a file name of a file corresponding to the single file message; and creating the first task and filling the determined first title name in a title region of the first task.

Abstract: An image forming apparatus includes a processor configured to switch one or more addresses to be displayed on a screen displaying the one or more addresses among plural addresses used for a transmission function for transmitting information according to a change in coordinates of a moving object without touching the screen.