Abstract: Embodiments for intelligent learning for explaining anomalies to a user by a processor. One or more anomalous records may be identified in a knowledge base. A list of ranked candidate explanations may be generated for the one or more anomalous records. An active learning dialog may be initiated with one or more users to increase accuracy of the knowledge base, a domain knowledge, and each of the ranked candidate explanations.

Abstract: The method for query training can include: determining a graphical representation, determining an inference network based on the graphical representation, determining a query distribution, sampling one or more train queries from the query distribution, and optionally determining a trained inference network by training the untrained inference network using the train query. The method can optionally include determining an inference query and determining an inference query result for the inference query using the trained inference network.

Abstract: Histopathological scoring can be based on the areas of certain types of cells or the expression of genotypic or phenotypic characteristics of those cells, as identified by a biological assay. Automating a scoring process with an image analysis algorithm includes correctly delineating the areas of interest, a process known as segmentation. The present systems and methods accomplish this segmentation using a generative adversarial network trained to generate masks covering each area of interest. The invention can perform both segmentation and classification by using a separate image band for each class. A scoring algorithm may utilize the classifications of, for example, a tumor area and an area of immune cell staining by interpreting the separate image bands of each area. Classification problems with more bands would use images with the equivalent number of bands. There is no limit to the number of bands an image can encode for each pixel.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for hierarchical weight-sparse convolution processing are described. An exemplary method comprises: obtaining an input tensor and a filter at a convolution layer of a neural network; segmenting the filter into a plurality of sub-filters; generating a hierarchical bit representation of the filter representing a plurality of non-zero weights in the filter, wherein the hierarchical bit representation comprises a first layer, the first layer comprising a plurality of bits respectively corresponding to the plurality of sub-filters in the filter, each of the plurality of bits indicating whether the corresponding sub-filter includes at least one non-zero weight; and performing multiply-and-accumulate (MAC) operations based on the hierarchical bit representation of the filter and the input tensor.

Abstract: A method for creating an interpretable model for healthcare predictions includes training, by a deep learning processor, a neural network to predict health information by providing training data, including multiple combinations of measured or observed health metrics and corresponding medical results, to the neural network. The method also includes determining, by the deep learning processor and using the neural network, prediction data including predicted results for the measured or observed health metrics for each of the multiple combinations of the measured or observed health metrics based on the training data. The method also includes training, by the deep learning processor or a learning processor, an interpretable machine learning model to make similar predictions as the neural network by providing mimic data, including combinations of the measured or observed health metrics and corresponding predicted results of the prediction data, to the interpretable machine learning model.

Abstract: A supervised learning processing (SLP) system and non-transitory, computer program product provides cooperative operation of a network of supervised learning processors to concurrently distribute supervised learning processor training, generate predictions, and provide prediction driven responses to input objects, such as NL statements. The SLP system includes SLP stages that are distributed across multiple SLP subsystems. Concurrently training SLP's provides accurate predictions of input objects and responses thereto, the SLP system and non-transitory, computer program product enhance the network by providing high quality value predictions and responses and avoiding potential training and operational delays. The SLP system can enhance the network of SLP subsystems by providing flexibility to incorporate multiple SLP models into the network and train at least a proper subset of the SLP models while concurrently using the SLP system and non-transitory, computer program product in commercial operation.

Abstract: The present disclosure relates to system(s) and method(s) for continuous business optimization of an organization based on a cognitive decision making process. In one embodiment, the method comprises generating an opportunity instance package associated with a business opportunity from a set of business opportunities associated with an organization based on analysis of a stream of raw data. Further, the method comprises generating a strategy using the opportunity instance package and one or more of a predictive technique, prescriptive technique and optimization technique. Furthermore, the method comprises generating a set of instruction associated with one or more actors associated with the organization based on the strategy, thereby enabling continuous business optimization of the organization based on a cognitive decision-making process.

Abstract: One or more multi-layer systems are used to perform inference. A multi-layer system may correspond to a node that receives a set of sensory input data for hierarchical processing, and may be grouped to perform processing for sensory input data. Inference systems at lower layers of a multi-layer system pass representation of objects to inference systems at higher layers. Each inference system can perform inference and form their own versions of representations of objects, regardless of the level and layer of the inference systems. The set of candidate objects for each inference system is updated to those consistent with feature-location representations for the sensors as well as object representations at lower layers. The set of candidate objects is also updated to those consistent with candidate objects from other inference systems, such as inference systems at other layers of the hierarchy or inference systems included in other multi-layer systems.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining a plurality of model representations of predictive models, each model representation associated with a respective user and expresses a respective predictive model, and selecting a model implementation for each of the model representations based on one or more system usage properties associated with the user associated with the corresponding model representation.

Abstract: A machine learning device is connected to a fiber laser device. The machine learning device observes, as a state variable representing a driving state of the fiber laser device, a state quantity including time-series data on output light detection results obtained by detecting a light output of laser light emitted from the fiber laser device and time-series data on reflected light detection results obtained by detecting reflected light of the laser light, and acquires determination data representing a failure occurrence situation in the fiber laser device as determined from a difference between the output light detection results and a light output instruction of the fiber laser device. The machine learning device learns a boundary condition for failure occurrence caused by the reflected light by using the state variable and the determination data.

Abstract: A monitor-mine-manage cycle is described, for example, for managing a data center, a manufacturing process, an engineering process or other processes. In various example, the following steps are performed as a continuous automated loop: receiving raw events from an observed system; monitoring the raw events and transforming them into complex events; mining the complex events and reasoning on results; making a set of proposed actions based on the mining; and managing the observed system by applying one or more of the proposed actions to the system. In various examples, the continuous automated loop proceeds while raw events are continuously received from the observed system and monitored. In some examples an application programming interface is described comprising programming statements which allow a user to implement a monitor-mine-manage loop.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for domain-specific pruning of neural networks are described. An exemplary method includes obtaining a first neural network trained based on a first training dataset; obtaining one or more second training datasets respectively from one or more domains; training, based on the first neural network and the one or more second training datasets, a second neural network comprising the first neural network and one or more branches extended from the first neural network. The one or more branches respectively correspond to the one or more domains, and each comprises one or more layers trained based on one of the one or more second training datasets. The method may further include: pruning the second neural network by reducing a number of active neurons; and applying the pruned second neural network for inferencing in the one or more domains.

Abstract: Methods and systems are provided for assigning computational problems to be solved by compute nodes that have artificial intelligence problem-solving capability. A method includes receiving a computational problem to be solved. Node-related processing attributes of the compute nodes are used to determine which one or more of the compute nodes are capable of solving the computational problem. One or more of the compute nodes are selected to handle the computational problem based upon the determination.

Abstract: Methods and systems for attributing browsing activity from two or more different network-connected devices to a single user are disclosed. In one aspect, cookies generated by the browsing activity of different unidentified devices at a website are received. A random forest classifier trained on probabilities output from a Gaussian mixture model is applied to the unidentified cookies to determine a probability that two different cookies were generated by the same user. In some embodiments, personalized content is then delivered to the user based on the characteristics of the paired cookies.

Abstract: A computer device may include a memory configured to store instructions and a processor configured to execute the instructions to train a generator neural network to simulate a network entity using a discriminator neural network that discriminates output associated with the network entity from output generated by the generator neural network. The computer device may be further configured to receive a set of input parameters associated with the simulated network entity; use the generator neural network to generate output for the simulated network entity based on the received set of input parameters; and apply the generated output for the simulated network entity to manage a communication network.

Abstract: An asynchronous convolutional neural network (CNN) can interpret a sequence of input data. An input value representing a sample of the sequence of input data is received by a computational unit (CU) in a layer of the asynchronous CNN. The CU calculates a dot product of the input value and a weight assigned to the CU to produce an activation value. A change detector (CD) associated with the CU detects a difference between the activation value and previous activation values. The CD determines whether the detected difference is significant, indicating that the sample of the sequence of input data includes a significant change. If the detected difference is significant, the activation value is supplied to at least one subsequent CU included in a subsequent layer of the asynchronous CNN.

Abstract: A method, system and computer-usable medium for performing cognitive computing operations comprising receiving streams of data from a plurality of data sources; processing the streams of data from the plurality of data sources, the processing the streams of data from the plurality of data sources performing data enriching for incorporation into a cognitive graph; defining a cognitive persona within the cognitive graph, the cognitive persona corresponding to an archetype user model, the cognitive persona comprising a set of nodes in the cognitive graph; associating a user with the cognitive persona; defining a cognitive profile within the cognitive graph, the cognitive profile comprising an instance of the cognitive persona that references personal data associated with the user; associating the user with the cognitive profile; and, performing a cognitive computing operation based upon the cognitive profile associated with the user.

Abstract: A method, system and computer-usable medium for performing cognitive computing operations comprising receiving streams of data from a plurality of data sources; processing the streams of data from the plurality of data sources, the processing the streams of data from the plurality of data sources performing data enriching for incorporation into a cognitive graph; defining a cognitive persona within the cognitive graph, the cognitive persona corresponding to an archetype user model, the cognitive persona comprising a set of nodes in the cognitive graph, links among the set of nodes being weighted to provide a weighted cognitive graph; associating a user with the cognitive persona; and, performing a cognitive computing operation based upon the cognitive persona associated with the user.

Abstract: Systems, methods, and apparatus, including computer programs encoded on a computer storage medium for processing a network input through a neural network having one or more initial neural network layers followed by a softmax output layer. In one aspect, the methods include obtaining a layer output generated by the one or more initial neural network layers and processing the layer output through the softmax output layer to generate a neural network output. Processing the layer output through the softmax output layer includes determining, for each possible output value, a number of occurrences in the layer output values; for each possible output value occurring in the layer output values, determining a respective exponentiation measure; determining a normalization factor for the layer output by combining the exponentiation measures in accordance with the number of occurrences of the possible output values; and determining, for each of layer output values, a softmax probability value.

Abstract: A data storage device includes a memory array for storing data; a host interface for providing an interface with a host computer running an application; a central control unit configured to receive a command in a submission queue from the application and initiate a search process in response to a search query command; a preprocessor configured to reformat data contained in the search query command and generate a reformatted data; and one or more data processing units configured to extract one or more features from the reformatted data and perform a data operation on the data stored in the memory array in response to the search query command and return matching data from the data stored in the memory array to the application via the host interface.