Abstract: A recommendation generator builds a network of interrelationships between venues, reviewers and users based on their attributes and reviewer and user reviews of the venues. Each interrelationship or link may be positive or negative and may accumulate with other links (or anti-links) to provide nodal links the strength of which are based on commonality of attributes among the linked nodes and/or common preferences that one node, such as a reviewer, expresses for other nodes, such as venues. The links may be first order (based on a direct relationship between, for instance, a reviewer and a venue) or higher order (based on, for instance, the fact that two venue are both liked by a given reviewer). The recommendation engine in certain embodiments determines recommended venues based on user attributes and venue preferences by aggregating the link matrices and determining the venues which are most strongly coupled to the user.

Abstract: A device may receive issue resolution information, associated with a cognitive model, including an item of issue resolution information that describes an issue and a resolution to the issue. The device may assign the item of issue resolution information to a domain hierarchy, where the assigning is associated with a first user. The device may generate a question and an answer corresponding to the item of issue resolution information, where the generating of the question and the answer is associated with a second user. The device may approve the question and the answer, where the approving is associated with a third user. The device may generate a question/answer (QA) pair for the question and the answer. The device may create a data corpus including the QA pair, and provide the data corpus to cause the cognitive model to be trained based on the data corpus.

Abstract: A predictive analytics system and method in the setting of multi-class classification are disclosed, for identifying systematic changes in an evaluation dataset processed by a fraud-detection model by examining the time series histories of an ensemble of entities such as accounts. The ensemble of entities is examined and processed both individually and in aggregate, via a set of features determined previously using a distinct training dataset. The specific set of features in question may be calculated from the entity's time series history, and may or may not be used by the model to perform the classification. Certain properties of the detected changes are measured and used to improve the efficacy of the predictive model.

Abstract: In configuring a processing system with an application made up of machine learning components, where the application has been trained on a set of training data, the application is executed on the processing system using another set of training data. Outputs of the application produced from the other set of training data identified that concur with ground truth data are identified. The components are adapted to produce outputs of the application that concur with the ground truth data using the identified outputs of the application.

Abstract: A method for hardware-implemented training of a feedforward artificial neural network is provided. The method comprises: generating a first output signal by processing an input signal with the network, wherein a cost quantity assumes a first cost value; measuring the first cost value; defining a group of at least one synaptic weight of the network for variation; varying each weight of the group by a predefined weight difference; after the variation, generating a second output signal from the input signal to measure a second cost value; comparing the first and second cost values; and determining, based on the comparison, a desired weight change for each weight of the group such that the cost function does not increase if the respective desired weight changes are added to the weights of the group. The desired weight change is based on the weight difference times ?1, 0, or +1.

Abstract: A method, system and computer-usable medium are disclosed for reducing labeled data imbalances when training an active learning system. The ratio of instances having positive labels or negative labels in a collection of labeled instances associated with an input category used for learning is determined. A first instance for annotation is selected from a collection of unlabeled instances if a first threshold for negative instances, and a first threshold confidence level of being a positive instance of the input category, have been met. A second instance for annotation is selected if a second threshold for positive instances, and a second threshold confidence level of being a negative instance of the input category, have been met. The first and second instances are respectively annotated with a positive and negative label and added to the collection of labeled instances, which are then used for training.

Abstract: A data analysis apparatus executes: acquiring a group of learning input data; setting a plurality of first hash functions; substituting each learning input data in each of the plurality of first hash functions to thereby calculate a plurality of first hash values; selecting, for the group of learning input data and for each of the plurality of first hash functions, a specific first hash value that satisfies a predetermined statistical condition from among the plurality of first hash values; setting a second hash function; substituting, for the group of learning input data, each specific first hash value in the second hash function to thereby calculate a plurality of second hash values; and generating a learning feature vector that indicates features of the group of learning input data by aggregating the plurality of second hash values corresponding to respective specific first hash values and obtained as a result of the calculation.

Abstract: Some embodiments perform, in a multi-layer neural network in a computing device, a convolution operation on input feature maps with multiple convolutional filters. The convolutional filters have multiple filter precisions. In other embodiments, electronic design automation (EDA) systems, methods, and computer-readable media are presented for adding such a multi-layer neural network into an integrated circuit (IC) design.

Abstract: An artificial intelligence (“AI”) engine having multiple independent processes on one or more computing platforms is disclosed, where the one or more computing platforms are located on premises of an organization such that i) the one or more computing platforms are configurable for one or more users in the organization having at least administrative rights on the one or more computing platforms in order to configure hardware components thereof to execute and load the multiple independent processes of the AI engine; ii) the one or more users of the organization are able to physically access the one or more computing platforms; and iii) the hardware components of the one or more computing platforms are connected to each other through a Local Area Network (LAN), and the LAN is configurable such that the one or more users in the organization have a right to control an operation of the LAN.

Abstract: A machine learning device of a controller observes, as state variables that express a current state of an environment, feeding amount data indicating a feeding amount per unit cycle of a tool and vibration amount data indicating a vibration amount of a cutting part of the tool when the cutting part of the tool passes through the workpiece. In addition, the machine learning device acquires determination data indicating a propriety determination result of the vibration amount of the cutting part of the tool when the cutting part of the tool passes through the workpiece. Then, the machine learning device learns the feeding amount per unit cycle of the tool when the cutting part of the tool passes through the workpiece in association with the vibration amount data, using the state variables and the determination data.

Abstract: A system and related method for building and deploying one or more inference models for use in remote condition monitoring of a first fleet of a first asset. The system includes model configuration data for subsequent use by a model builder application to construct one or more desired inference models for the first asset. The model configuration data is customized to the first asset and the desired one or more inference models, and is provided in a format which is easily readable and editable by a user of the system. The model configuration data is separate from the underlying processing algorithms which are employed by the model builder application in the constructing of the one or more desired inference models during a learning mode of operation of the system.

Abstract: Various embodiments are generally directed to techniques to reduce inputs of a machine learning model (MLM) and increase path efficiency as a result. A method for reducing an MLM includes: receiving a machine learning (ML) dataset, partitioning the ML dataset into a first dataset, a second dataset, a third dataset, and a fourth dataset, training, validating, and testing the MLM using one or more of the first dataset, the second dataset, and the third dataset, after testing the MLM, automatically ranking an importance associated with each input of the MLM using the fourth dataset, and reducing a plurality of inputs of the MLM based on the automatic ranking.

Abstract: A system generates trade deduction settlement rules and associated confidence scores independent of buyer specifications. A machine learning equipped rewards based method performed by the system analyzes historically matched deductions and promotions to understand patterns. Penalties are applied to outdated rules, and recent trends are promoted through rewards. All available deduction-promotion combinations may be analyzed in batches for a given time period at each pair level within an artificial intelligence model of the method. A rules selector selects the most recurring patterns along those combinations based upon definable thresholds. The system finds hidden patterns to provide suggestions for trade deduction settlement. The system further captures the rules and evolves the rules over time.

Abstract: In one aspect, a request for web content is received from a user device communicatively coupled to the processing device via the network. In response to receiving the request, user information associated with the user is determined. Predicted responses of the user to each variation of a plurality of variations of the web content are determined using prediction models and the user information. The prediction models include one or more decision trees generated using a splitting criterion requiring a minimum number of positive responses to a variation and a minimum number of negative responses to the variation as a condition of considering the possible split. The variation determined to have a threshold likelihood of yielding a predicted positive response of the predicted responses is selected based on the user information. The variation is transmitted to the user device via the network.

Abstract: Embodiments provide a computer implemented method, in a data processing system including a processor and a memory including instructions which are executed by the processor to cause the processor to train an enhanced chatflow system, the method including: ingesting a corpus of information including at least one user input node corresponding to a user question and at least one variation for each user input node; for each user input node: designating the node as a class; storing the node in a dialog node repository; designating each of the at least one variations as training examples for the designated class; converting the classes and the training examples into feature vector representations; training one or more training classifiers using the one or more feature vector representations of the classes; and training classification objectives using the one or more feature vector representations of the training examples.

Abstract: A computing system computes a variable relevance using a trained tree model. (A) A next child node is selected. (B) A number of observations associated with the next child node is computed. (C) A population ratio value is computed. (D) A next leaf node is selected. (E) First observations are identified. (F) A first impurity value is computed for the first observations. (G) Second observations are identified when the first observations are associated with the descending child nodes. (H) A second impurity value is computed for the second observations. (I) A gain contribution is computed. (J) A node gain value is updated. (K) (D) through (J) are repeated. (L) A variable gain value is updated for a variable associated with the split test. (M) (A) through (L) are repeated. (N) A set of relevant variables is selected based on the variable gain value.

Abstract: Rating models may be generated by obtaining a plurality of consumption values, obtaining a plurality of rating values, training a model that estimates consumption values and rating values by utilizing a plurality of consumer attributes for each consumer, a plurality of item attributes for each item, and a plurality of weights for each attribute of each combination of a consumer and an item. Each estimated consumption value is a function of the plurality of weights for each attribute of each combination of each consumer and each item that corresponds with the estimated consumption value, and each estimated rating value is a function of the plurality of consumer attributes of a consumer that corresponds with the estimated rating value, the plurality of item attributes of an item that corresponds with the estimated rating value, and the plurality of weights that corresponds with the estimated rating value.

Abstract: A system and method for controlling a nodal network. The method includes estimating an effect on the objective caused by the existence or non-existence of a direct connection between a pair of nodes and changing a structure of the nodal network based at least in part on the estimate of the effect. A nodal network includes a strict partially ordered set, a weighted directed acyclic graph, an artificial neural network, and/or a layered feed-forward neural network.

Abstract: Methods, and systems, including computer programs encoded on computer storage media for generating data items. A method includes reading a glimpse from a data item using a decoder hidden state vector of a decoder for a preceding time step, providing, as input to a encoder, the glimpse and decoder hidden state vector for the preceding time step for processing, receiving, as output from the encoder, a generated encoder hidden state vector for the time step, generating a decoder input from the generated encoder hidden state vector, providing the decoder input to the decoder for processing, receiving, as output from the decoder, a generated a decoder hidden state vector for the time step, generating a neural network output update from the decoder hidden state vector for the time step, and combining the neural network output update with a current neural network output to generate an updated neural network output.

Abstract: The present disclosure provides systems and methods for debugging neural networks. In one example, a computer-implemented method is provided, which includes obtaining, by one or more computing devices, one or more inputs from an input corpus. The method further includes mutating, by the one or more computing devices, the one or more inputs and providing the one or more mutated inputs to a neural network; obtaining, by the one or more computing devices as a result of the neural network processing the one or more mutated inputs, a set of coverage arrays; determining, by the one or more computing devices based at least in part on the set of coverage arrays, whether the one or more mutated inputs provide new coverage; and upon determining that the one or more mutated inputs provide new coverage, adding the one or more mutated inputs to the input corpus.