Abstract: A method for action automation includes determining, using an electronic device, an action based on domain information. Activity patterns associated with the action are retrieved. For each activity pattern, a candidate action rule is determined. Each candidate action rule specifies one or more pre-conditions when the action occurs. One or more preferred candidate action rules are determined from multiple candidate action rules for automation of the action.

Abstract: A method may include embedding, in a hidden layer and/or an output layer of a first machine learning model, a first digital watermark. The first digital watermark may correspond to input samples altering the low probabilistic regions of an activation map associated with the hidden layer of the first machine learning model. Alternatively, the first digital watermark may correspond to input samples rarely encountered by the first machine learning model. The first digital watermark may be embedded in the first machine learning model by at least training, based on training data including the input samples, the first machine learning model. A second machine learning model may be determined to be a duplicate of the first machine learning model based on a comparison of the first digital watermark embedded in the first machine learning model and a second digital watermark extracted from the second machine learning model.

Abstract: Systems and methods are disclosed for managing a generative artificial intelligence (AI) model to improve performance. Managing the generative AI model includes using a second generative AI model to generate outputs from similar inputs and comparing the outputs of the generative AI models to determine their similarity. The second generative AI model is trained using fresher training data but may not be manually supervised and adjusted to the level of the generative AI model being managed. As such, an output of the second generative AI model is compared to an output of the managed generative AI model by a classification model to determine a relevance of the output from the managed generative AI model. An output of the classification model is used to perform various suitable policies to optimize the performance of the managed generative AI model, such as providing alternate outputs, preventing providing the output, or retraining the model.

Abstract: A method includes receiving a first query by a computing device and assigning the first query to a plurality of cognitive engines, wherein each of the plurality of cognitive engines include different characteristics for processing data. The method also includes, responsive to receiving a response from each of the plurality of cognitive engines for the first query, comparing the received responses from the plurality of cognitive engines. The method also included responsive to determining a difference between a first response from a first cognitive engine and a second response from a second cognitive engine is above a predetermined threshold value, performing a response mediation process until the difference is below the predetermined threshold value. The method also includes selecting a first final response from the received responses for the first query and the second query and displaying the first final response to a user.

Abstract: A computer-implemented method for determining the volume of activation of neural tissue. In one embodiment, the method uses one or more parametric equations that define a volume of activation, wherein the parameters for the one or more parametric equations are given as a function of an input vector that includes stimulation parameters. After receiving input data that includes values for the stimulation parameters and defining the input vector using the input data, the input vector is applied to the function to obtain the parameters for the one or more parametric equations. The parametric equation is solved to obtain a calculated volume of activation.

Abstract: A system may include a processor and a memory. The memory may include program code that provides operations when executed by the processor. The operations may include: partitioning, based at least on a resource constraint of a platform, a global machine learning model into a plurality of local machine learning models; transforming training data to at least conform to the resource constraint of the platform; and training the global machine learning model by at least processing, at the platform, the transformed training data with a first of the plurality of local machine learning models.

Abstract: An indication of a selection of an entry associated with a machine learning model is received. One or more interpretation views associated with one or more machine learning models are dynamically updated based on the selected entry.

Abstract: A computational method via a hybrid processor comprising an analog processor and a digital processor includes determining a first classical spin configuration via the digital processor, determining preparatory biases toward the first classical spin configuration, programming an Ising problem and the preparatory biases in the analog processor via the digital processor, evolving the analog processor in a first direction, latching the state of the analog processor for a first dwell time, programming the analog processor to remove the preparatory biases via the digital processor, determining a tunneling energy via the digital processor, determining a second dwell time via the digital processor, evolving the analog processor in a second direction until the analog processor reaches the tunneling energy, and evolving the analog processor in the first direction until the analog processor reaches a second classical spin configuration.

Abstract: Systems, methods, devices, and other techniques are described herein for training and using neural networks to encode inputs and to process encoded inputs, e.g., to reconstruct inputs from the encoded inputs. A neural network system can include an encoder neural network, a trusted decoder neural network, and an adversary decoder neural network. The encoder neural network processes a primary neural network input and a key input to generate an encoded representation of the primary neural network input. The trusted decoder neural network processes the encoded representation and the key input to generate a first estimated reconstruction of the primary neural network input. The adversary decoder neural network processes the encoded representation without the key input to generate a second estimated reconstruction of the primary neural network input. The encoder and trusted decoder neural networks can be trained jointly, and these networks trained adversarially to the adversary decoder neural network.

Abstract: A method includes defining model attributes of a machine model that organizes feedback data into topic groups based on similarities in concepts in the feedback data. The model attributes include a topic model number that defines how many topic groups are to be created, a hyperparameter optimization alpha value, and/or a hyperparameter optimization beta value. The method also includes generating the machine model using the model attributes that are defined and the feedback data, and applying the machine model to the feedback data to divide different portions of the feedback data into the different topic groups based on contents of the feedback data, the topic model number, the hyperparameter optimization alpha value, and/or the hyperparameter optimization beta value.

Abstract: Disclosed in a processor chip configured to perform neural network processing. The processor chip includes a memory, a first processor configured to perform neural network processing on a data stored in the memory, a second processor and a third processor, and the second processor is configured to transmit a control signal to the first processor and the third processor to cause the first processor and the third processor to perform an operation.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for a neural network system comprising one or more gated linear networks. A system includes: one or more gated linear networks, wherein each gated linear network corresponds to a respective data value in an output data sample and is configured to generate a network probability output that defines a probability distribution over possible values for the corresponding data value, wherein each gated linear network comprises a plurality of layers, wherein the plurality of layers comprises a plurality of gated linear layers, wherein each gated linear layer has one or more nodes, and wherein each node is configured to: receive a plurality of inputs, receive side information for the node; combine the plurality of inputs according to a set of weights defined by the side information, and generate and output a node probability output for the corresponding data value.

Abstract: Simulating uncertainty in an artificial neural network is provided. Aleatoric uncertainty is simulated to measure what the artificial neural network does not understand from sensor data received from an object operating in a real-world environment by adding random values to edge weights between nodes in the artificial neural network during backpropagation of output data of the artificial neural network and measuring impact on the output data by the added random values to the edge weights between the nodes. Epistemic uncertainty is simulated to measure what the artificial neural network does not know by dropping out a selected node from each respective layer of the artificial neural network during forward propagation of the sensor data and measuring impact of dropped out nodes on the output data of the artificial neural network. An action corresponding to the object is performed based on the impact of simulating the aleatoric and epistemic uncertainty.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an actor neural network used to select actions to be performed by an agent interacting with an environment. One of the methods includes obtaining a minibatch of experience tuples; and updating current values of the parameters of the actor neural network, comprising: for each experience tuple in the minibatch: processing the training observation and the training action in the experience tuple using a critic neural network to determine a neural network output for the experience tuple, and determining a target neural network output for the experience tuple; updating current values of the parameters of the critic neural network using errors between the target neural network outputs and the neural network outputs; and updating the current values of the parameters of the actor neural network using the critic neural network.

Abstract: A method of operating a neural network system includes parsing, by a processor, at least one item of information related to a neural network operation from an input neural network model; determining, by the processor, information of at least one dedicated hardware device; and generating, by the processor, a reshaped neural network model by changing information of the input neural network model according to a result of determining the information of the at least one dedicated hardware device such that the reshaped neural network model is tailored for execution by the dedicated hardware device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving training data for multiple datasets that include information about a computing process. The training data is received at a computing system that includes a data manager, a data classifier, and a machine learning (ML) system. The data classifier annotates the training data as being associated with a particular dataset and as being descriptive of computing processes executed to perform transactions. The ML system receives the annotated training data and data about a transaction operation of the system, trains a predictive model to generate prediction data that indicates a runtime condition of the system, and provides the prediction data to a process automation module of the system. The module executes process automation scripts to remediate the computing process, where the computing process is executed by the system to perform the real-time transaction operation.

Abstract: The subject technology determines input parameters and an output format of algorithms for a particular functionality provided by an electronic device. The subject technology determines an order of the algorithms for performing the particular functionality based on temporal dependencies of the algorithms, and the input parameters and the output format of the algorithms. The subject technology generates a graph based on the order of the algorithms, the graph comprising a set of nodes corresponding to the algorithms, each node indicating a particular processor of the electronic device for executing an algorithm. Further, the subject technology executes the particular functionality based on performing a traversal of the graph, the traversal comprising a topological traversal of the set of nodes and the traversal being based on a score indicating whether selection of a particular node for execution over another node enables a greater number of processors to be utilized at a time.

Abstract: A method for method for classification of virtual reality (VR) content for use in head mounted displays (HMDs). The method includes accessing a model that identifies a plurality of learned patterns associated with the generation of corresponding baseline VR content that is likely to cause discomfort. The method includes executing a first application to generate first VR content. The method includes extracting data associated with simulated user interactions with the first VR content, the extracted data generated during execution of the first application. The method includes comparing the extracted data to the model to identify one or more patterns in the extracted data matching at least one of the learned patterns from the model such that the one or more patterns are likely to cause discomfort.

Abstract: This invention provides an autonomic method for controlling an algorithm on a multi-terminal computing system, wherein the algorithm is configured to analyse diagnostic data for each terminal and an outcome of the analysis is a first action or a second action, and a device for implementing the method, the method comprising the steps of: receiving a first set of data for the multi-terminal computing system; applying the algorithm to the first set of data to classify each terminal in the multi-terminal computing system as being associated with either a first action or second action; re-classifying a first subset of terminals classified as being associated with the first action as being associated with the second action; and applying the first actions, second actions, and reclassified second actions respectively to each terminal in the multi-terminal computing system.

Abstract: A method and an apparatus to build a machine learning based network model are described. For example, processing circuitry of an information processing apparatus obtains a data processing procedure of a first network model and a reference dataset that is generated by the first network model in the data processing procedure. The data processing procedure includes a first data processing step. Further, the processing circuitry builds a first sub-network in a second network model of a neural network type. The second network model is the machine learning based network model to be built. The first sub-network performs the first data processing step. Then, the processing circuitry performs optimization training on the first sub-network by using the reference dataset.