Abstract: Provided herein is a system for creating, modifying, deploying and running intelligent systems by combining and customizing the function and operation of reusable component modules arranged into neural processing graphs which direct the flow of signals among the modules, analogous in part to biological brain structure and operation as compositions of variations on functional components and subassemblies.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains validated training data containing a first set of content items and a first set of classification tags for the first set of content items. Next, the system uses the validated training data to produce a statistical model for classifying content using a set of dimensions represented by the first set of classification tags. The system then uses the statistical model to generate a second set of classification tags for a second set of content items. Finally, the system outputs one or more groupings of the second set of content items by the second set of classification tags to improve understanding of content related to the set of dimensions without requiring a user to manually analyze the second set of content items.

Abstract: A recommendation system uses artificial intelligence to identify, based on negative sentiment cues from users, item attributes, such as keywords, that users may find offensive or undesirable. The negative sentiment cues may be explicit (e.g., a user selects an option not to view a particular recommendation again), implicit (e.g., a user does not interact with recommendations relating to an attribute), or both. The system may use a computer model generated based on these identified attributes to filter or modify recommendations to a user or group of users. For instance, if a particular keyword is identified as highly offensive to a group of users, items associated with the keyword may be filtered from item recommendations presented to the group of users. If an attribute is identified as moderately offensive to a user, items associated with the attribute may be down-weighted in item recommendations presented to the user.

Abstract: A method includes determining, by a processor of a computing device, an expected performance or reliability of a first neural network of a first plurality of neural networks. The expected performance or reliability is determined based on a vector representing at least a portion of the first neural network, where the first neural network is generated based on an automated generative technique (e.g., a genetic algorithm) and where the first plurality of neural networks corresponds to a first epoch of the automated generative technique. The method also includes responsive to the expected performance or reliability of the first neural network failing to satisfy a threshold, adjusting a parameter of the automated generative technique. The method further includes, during a second epoch of the automated generative technique, generating a second plurality of neural networks based at least in part on the adjusted parameter.

Abstract: Providing automatic initial responses to service requests. An automated support engine receives a service request including a problem description from a client. A text analysis component analyzes the problem description to identify an issue. A search component searches response reference sources to identify a set of suggested solutions and a set of reference materials associated with the issue. The response reference sources include structured data materials and unstructured data materials. The automated support engine combines the set of suggested solutions and a set of links corresponding to the set of reference materials to generate an automatic initial response. The automated support engine sends the automatic initial response to the client to assist a user in resolving the identified issue.

Abstract: A compression coding apparatus for artificial neural network, including memory interface unit, instruction cache, controller unit and computing unit, wherein the computing unit is configured to perform corresponding operation to data from the memory interface unit according to instructions of controller unit; the computing unit mainly performs three steps operation: step one is to multiply input neuron by weight data; step two is to perform adder tree computing and add the weighted output neuron obtained in step one level-by-level via adder tree, or add bias to output neuron to get biased output neuron; step three is to perform activation function operation to get final output neuron. The present disclosure also provides a method for compression coding of multi-layer neural network.

Abstract: Methods for training machines to categorize data, and/or recognize patterns in data, and machines and systems so trained. More specifically, variations of the invention relates to methods for training machines that include providing one or more training data samples encompassing one or more data classes, identifying patterns in the one or more training data samples, providing one or more data samples representing one or more unknown classes of data, identifying patterns in the one or more of the data samples of unknown class(es), and predicting one or more classes to which the data samples of unknown class(es) belong by comparing patterns identified in said one or more data samples of unknown class with patterns identified in said one or more training data samples.

Abstract: Provided is a process, including: obtaining a first training dataset of subject-entity records; training a first machine-learning model on the first training dataset; forming virtual subject-entity records by appending members of a set of candidate action sequences to time-series of at least some of the subject-entity records; forming a second training dataset by labeling the virtual subject-entity records with predictions of the first machine-learning model; and training a second machine-learning model on the second training dataset.

Abstract: A method, apparatus, and computer program product are provided for generating a set of token sequences for at least a portion of a database, wherein each token in a sequence represents a respective database entity of the database; assigning, for each token in the set of token sequences, at least one corresponding vector from a set of vectors of a same dimension, wherein the at least one corresponding vector encodes relationships between the database entity of a token and other database entities of other tokens of the set of token sequences; and extracting, using a query language, information from the database based at least in part on the relationships encoded by the assigned vectors.

Abstract: The present disclosure provides an operation-path recommendation method and apparatus. In the present disclosure, by an operation-path recommendation apparatus, a blood vessel graph model is generated based on patient's anatomical information, a plurality of candidate paths between defined start and destination points is extracted; node information on at least one node in each of the candidate paths is extracted; a cost function is applied to each candidate path, based on the extracted node information.

Abstract: Approaches, techniques, and mechanisms are disclosed for generating, enhancing, applying and updating knowledge neurons for providing decision making information to a wide variety of client applications. Domain keywords for knowledge domains are generated from domain data of selected domain data sources, along with keyword values for the domain keywords, and are used to generate knowledge artifacts for inclusion in knowledge neurons. These knowledge neurons may be enhanced by domain knowledge data sets found in various data sources and used to generate neural responses to neural queries received from the client applications. Neural feedbacks may be used to update and/or generate knowledge neurons.

Abstract: According to one embodiment of the present invention, a prediction system is provided. The system comprises a first data decomposition facility configured to decompose a provided time series of consumption data into a plurality of different training sets for different types of days and a second data decomposition facility configured to decompose each one of the plurality of training sets into at least a seasonal component and a trend component. The system further comprises a regression facility configured to perform a regression analysis on the decomposed consumption data based on at least the trend component and chronological information associated with the consumption data of the respective training set to train a prediction function and a prediction facility configured to estimate predicted energy consumption data based on the trained prediction function and the type of a day for which the prediction is performed.

Abstract: A method is provided for estimating past data by identifying a high frequency data set for a defined time period. A pattern is calculated for the high frequency data set and then the pattern is applied to a low frequency data set in a past time period to estimate a high frequency query point.

Abstract: A machine provides a system and interface to deploy and manage pre-defined analytical models across various compute engines or run time environments, e.g., by exposing analytical model deployment and management parameters to a user while abstracting model deployment activities. The machine also determines proper run time environments for the pre-defined analytical model and verifies the pre-defined analytical model. The machine also provides a dynamically reconfigurable user interface for controlling the machine.

Abstract: A system for bit-serial computation in a neural network is described. The system may be embodied on an integrated circuit and include one or more bit-serial tiles for performing bit-serial computations in which each bit-serial tile receives input neurons and synapses, and communicates output neurons. Also included is an activation memory for storing the neurons and a dispatcher and a reducer. The dispatcher reads neurons and synapses from memory and communicates either the neurons or the synapses bit-serially to the one or more bit-serial tiles. The other of the neurons or the synapses are communicated bit-parallelly to the one or more bit-serial tiles, or according to a further embodiment, may also be communicated bit-serially to the one or more bit-serial tiles. The reducer receives the output neurons from the one or more tiles, and communicates the output neurons to the activation memory.

Abstract: A processor includes a front end to decode an instruction, an allocator to pass the instruction to a nearest neighbor logic unit (NNLU) to execute the instruction, and a retirement unit to retire the instruction. The NNLU includes logic to determine input of the instruction for which nearest neighbors will be calculated, transform the input, retrieve candidate atoms for which the nearest neighbors will be calculated, compute distance between the candidate atoms and the input, and determine the nearest neighbors for the input based upon the computed distance.

Abstract: Computer-based systems and methods are provided for generating a narrative computer scoring model for assessing story narratives. In one embodiment, supervised machine learning is used to generate the narrative computer scoring model. For example, a collection of training story narratives with assigned scores may be used to train the model. In one embodiment, each training story narrative is processed to extract features that signify content relevance, collocation of commonly used words, coherency, detailing, and expressions of sentiment. These features, as well as others, may be selectively used to train a narrative computer scoring model. Once trained, the model can be used to automatically evaluate story narratives and assign appropriate scores.

Abstract: Lookalike models can select users that are predicted to share characteristics with a specified set of seed users. The processing requirements for lookalike models can be decreased by identifying features that have low impact on model accuracy, and therefore can be excluded from creating models. Also, by identifying preferred seed sources and training parameters, accurate lookalike models can be created with less overhead and in less time. The features and training parameters can be identified by obtaining a sample seed set, extracting seeds with a defined set of features, and using the remaining training seeds to train a model. Performance of this model can be compared to a standard model to see if the model performs well. If so, features excluded from the features used to create the model, a seed source, or training parameters used to create the model can be selected.

Abstract: This disclosure is directed to the automated generation of Machine Learning (ML) models. The system receives a user directive containing one or more requirements for building the ML model. The system further identifies common requirements between the user directive and one or more prior user directives and associates characteristics of the prior user directive, or model generated therefrom, with the user directive. The system further associates performance values generated by continuous monitoring of deployed ML models to individual characteristics of the user directive used to generate each of the deployed ML models. The system continuously improves model generation efficiency, model performance, and first run performance of individual ML models by learning from the improvements made to one or more prior ML models having similar characteristics.

Abstract: An apparatus can include a first state machine engine configured to receive a first portion of a data stream from a processor and a second state machine engine configured to receive a second portion of the data stream from the processor. The apparatus includes a buffer interface configured to enable data transfer between the first and second state machine engines. The buffer interface includes an interface data bus coupled to the first and second state machine engines. The buffer interface is configured to provide data between the first and second state machine engines.