Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a target sequence including a respective output at each of multiple output time steps from respective encoded representations of inputs in an input sequence. The method includes, for each output time step, starting from the position, in the input order, of the encoded representation that was selected as a preceding context vector at a preceding output time step, traversing the encoded representations until an encoded representation is selected as a current context vector at the output time step. A decoder neural network processes the current context vector and a preceding output at the preceding output time step to generate a respective output score for each possible output and to update the hidden state of the decoder recurrent neural network. An output is selected for the output time step using the output scores.

Abstract: Described are methods and systems to identify analyzing a social network to predict member actions, queries, or ranks within a social networking system. According to various embodiments, the system detects changes within a first data set of a first member. The system identifies an entity associated with the change in the first data set, determines an action probability of the entity in response to the change, and identifies a second data set associated with a second member having at least one common element with the first data set. The system identifies a set of elements in the first data set and an entity data set corresponding to the change and generates a customized user interface screen comprising a representation of the entity and a portion of the set of elements.

Abstract: Techniques are described herein that are capable of performing intent-based scheduling via a digital personal assistant. For instance, an intent of user(s) to perform an action (a.k.a. activity) may be used to schedule time (e.g., on a calendar of at least one of the user(s)) in which the action is to be performed. Examples of performing an action include but are not limited to having a meeting, working on a project, participating in a social event, exercising, and reading.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using normalized target outputs. One of the methods includes updating current values of the normalization parameters to account for the target output for the training item; determining a normalized target output for the training item by normalizing the target output for the training item in accordance with the updated normalization parameter values; processing the training item using the neural network to generate a normalized output for the training item in accordance with current values of main parameters of the neural network; determining an error for the training item using the normalized target output and the normalized output; and using the error to adjust the current values of the main parameters of the neural network.

Abstract: A hardware-based programmable deep learning processor (DLP) is proposed, wherein the DLP comprises with a plurality of accelerators dedicated for deep learning processing. Specifically, the DLP includes a plurality of tensor engines configured to perform operations for pattern recognition and classification based on a neural network. Each tensor engine includes one or more matrix multiplier (MatrixMul) engines each configured to perform a plurality of dense and/or sparse vector-matrix and matrix-matrix multiplication operations, one or more convolutional network (ConvNet) engines each configured to perform a plurality of efficient convolution operations on sparse or dense matrices, one or more vector floating point units (VectorFPUs) each configured to perform floating point vector operations, and a data engine configured to retrieve and store multi-dimensional data to both on-chip and external memories.

Abstract: A machine learning device, which performs a task using a plurality of industrial machines and learns task sharing for the plurality of industrial machines, includes a state variable observation unit which observes state variables of the plurality of industrial machines; and a learning unit which learns task sharing for the plurality of industrial machines, on the basis of the state variables observed by the state variable observation unit.

Abstract: System and method for automatic entity relationship (ER) model generation for services as software is disclosed. ER model generation by automated knowledge acquisition is disclosed, and automation of knowledge generation process is disclosed. Information extraction process is automated and multilevel validation of information extraction process is provided. System comprises training module to train information extraction model, and knowledge generation module for population of ER model. Standard Operators are generated based on the ER model so generated (populated). Context aware entity extraction is implemented for the ER model generation. System and method leverages existing ER model to make the system self-learning and intelligent, and provides common platform for knowledge generation from different data sources comprising documents, database, website, web corpus, and blog.

Abstract: An apparatus and method are provided to perform constrained optimization of a constrained property of an apparatus, which is complex due to having several components, and these components are configurable in real-time. The optimization is achieved by detecting values of the constrained property and a plurality of other properties of the apparatus when the apparatus is configured in a first subset of the plurality of configurations. A model is learned using the detected values of the constrained property. The model represents the constrained property and can also represent other properties as a function of the configurations. The model can also include estimated uncertainties of the constrained property in the model. Then, using the d model and the estimated uncertainties, the optimal configuration can be selected to minimize an error value (e.g., the difference between a desired value and an observed value of the at least one constrained property).

Abstract: Methods and systems are provided herein for calibrating subject data based on reference data, so that the calibrated subject data more closely represents a target population. The methods and systems include partitioning a reference data set into a plurality of reference data partitions using a data partitioning scheme, each reference data partition associated with a characteristic; and partitioning a subject data set into a plurality of subject data partitions using the data partitioning scheme, each subject data partition associated with a characteristic that corresponds to the characteristic associated with a reference data partition of the plurality of reference data partitions; identifying a variable present in the reference data set that is not present in the subject data set; and calculating a value of the variable for each reference data partition based on a rate of occurrence of the variable in each reference data partition.

Abstract: A method, system and computer readable medium for generating a cognitive insight comprising: receiving training data, the training data being based upon interactions between a user and a cognitive learning and inference system; performing a hierarchical topic machine learning operation on the training data; generating a cognitive profile based upon the information generated by performing the hierarchical topic machine learning operation; and, generating a cognitive insight based upon the cognitive profile generated using the hierarchical topic machine learning operation.

Abstract: A method, system and computer readable medium for generating a cognitive insight comprising: receiving training data, the training data being based upon interactions between a user and a cognitive learning and inference system; performing a plurality of machine learning operations on the training data; generating a cognitive profile based upon the information generated by performing the plurality of machine learning operations; and, generating a cognitive insight based upon the profile generated using the plurality of machine learning operations.

Abstract: A method of determining the effect that changes in input variables have on changes in the output of a time series model, between two instances of time, produces variable attributions that satisfy the Shapley fairness properties of efficiency, symmetry, linearity, and null player.

Abstract: The present invention relates to artificial neural networks, for example, deep neural networks. In particular, the present invention relates to a compression method considering load balance for deep neural networks and the device thereof. More specifically, the present invention relates to how to compress dense neural networks into sparse neural networks in an efficient way so as to improve utilization of resources of the hardware platform.

Abstract: The Automata Processor Workbench (AP Workbench) is an application for creating and editing designs of AP networks (e.g., one or more portions of the state machine engine, one or more portions of the FSM lattice, or the like) based on, for example, an Automata Network Markup Language (ANML). For instance, the application may include a tangible, non-transitory computer-readable medium configured to store instructions executable by a processor of an electronic device, wherein the instructions include instructions to represent an automata network as a graph.

Abstract: A method and a system are provided for predicting a non-linear relationship between a plurality of parameters in a deep neural network framework. The method comprises receiving, by an application server, a plurality of parameter values associated with the plurality of parameters. The method further comprises selecting, by the application server, an activation function based on a desired output. In an embodiment, the desired output is based on an industry type and an application area of the plurality of parameters. The method further comprises predicting, by the application server, the non-linear relationship between the plurality of parameters by modelling the deep neural network framework based on the selected activation function.

Abstract: In many environments, rules are trained on historical data to predict an outcome likely to be associated with new data. Described is a ruleset which predicts the probability of a particular outcome. Roughly described, an individual identifies a ruleset, where each of the rules has a plurality of conditions and also indicates a rule-level probability of a predetermined classification. The conditions indicate a relationship (e.g. ‘<’ or ‘!<’) between an input feature and a corresponding value. The rules are evaluated against input data to derive a certainty for each condition, and aggregated to a rule-level certainty. The rule probabilities are combined using the rule-level certainty values to derive a probability output for the ruleset, which can be used to provide a basis for decisions. In an embodiment, the per-condition certainty values are fuzzy values aggregated by fuzzy logic. A novel genetic algorithm can be used to derive the ruleset.

Abstract: Application tool recommendations are described. Initially, application usage data is captured indicating tools used and actions performed by existing users of an application. This application usage data is converted into human-readable words describing the tools used and actions performed. This allows natural language processing techniques to be applied to the converted data. Through natural language processing, importance scores for the tools and actions can be computed and tasks performed with the application determined. The natural language processing techniques are also used to build task prediction models based on the importance scores and determined tasks. These task prediction models indicate probabilities of the determined tasks to be next performed by a current application user. A task having the highest probability of being next performed is predicted as the next task. Tool recommendations associated with the predicted next task are then presented to aid the user with the predicted next task.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating data items. One of the systems is a neural network system comprising a memory storing a plurality of template data items; one or more processors configured to select a memory address based upon a received input data item, and retrieve a template data item from the memory based upon the selected memory address; an encoder neural network configured to process the received input data item and the retrieved template data item to generate a latent variable representation; and a decoder neural network configured to process the retrieved template data item and the latent variable representation to generate an output data item.

Abstract: A method detects an event or anomaly in real-time and triggers an action based thereon. A stream of data is received from data sources. The data includes at least two categorical features and a real-value measurement. Sketching is performed on the features using min-wise hashing to create sketches of the data. A regression tree is learnt on the sketches so as to estimate a mean squared error. It is determined whether an event or anomaly exists based on the mean squared error. An action is triggered based on at least one of a type, location or magnitude of the determined event or anomaly.

Abstract: A method and/or system for heterogeneous predictive models generation based on sampling of big data is disclosed. The method involves receiving a dataset and a target column associated with the dataset at a data processing engine from a distributed data warehouse. One or more columns associated with the dataset are classified at the data processing engine as a categorical column or a continuous column. One or more parameters in the dataset are identified to extract a sample data from the dataset. The sample data from the dataset is extracted based on the identified one or more parameters. One or more rank ordered machine learning algorithms are recommended to one or more users, to generate one or more predictive models from the sample data. One or more heterogeneous predictive models are generated based on the rank ordered algorithm through one or more iterations.