Abstract: An ontology topic is selected and a pretrained predictive language model is primed to create a predictive primed model based on one or more ontological rules corresponding to the selected ontology topic. Using the predictive primed model, natural language text is generated based on the ontology topic and guidance of a prediction steering component. The predictive primed model is guided in selecting text that is predicted to be appropriate for the ontology topic and the generated natural language text. The generated natural language text is processed to generate extracted ontology rules and the extracted ontology rules are compared to one or more rules of an ontology rule database that correspond to the ontology topic. A check is performed to determine if a performance of the ontology extractor is acceptable.

Abstract: A computer-implemented method may include processors configured for receiving input data corresponding to a knowledge base comprising a plurality of propositional logic clauses, generating output data corresponding to a first set of logical rules and a first set of facts based on the plurality of propositional logic clauses, accumulating the first set of facts to generate accumulated facts, generating a model graph based on the accumulated facts and the first set of logical rules, alternating reasoning and learning passes at the model graph until convergence to generate a second set of logical rules and a second set of facts, and generating a third set of logical rules and a third set of facts, wherein the third set of logical rules and the third set of facts exceed a first predetermined threshold.

Abstract: An embodiment may include a processor that identifies a plurality of weights from the propositional logical neural network. The embodiment may convert the plurality of weights into a sparse matrix. The embodiment may convert a training set into a plurality of bound vectors. The embodiment may update the sparse matrix using a graphical processing unit (GPU). The embodiment may compute a loss parameter and based on determining the loss function is below threshold, update the plurality of weights of the propositional neural network.

Abstract: Methods and systems for generating representative data. A generator is configured to create, using a learning model, one or more generated records based on a plurality of training records obtained from a sensitive database. A discriminator is trained to identify the generated records as being generated based on the training records and a privacy adversary is trained to identify a training sample as being more similar to a distribution of the generated records than a distribution of the reference records.

Abstract: Word sense disambiguation using a glossary layer embedded in a deep neural network includes receiving, by one or more processors, input sentences including a plurality of words. At least two words in the plurality of words are homonyms. The one or more processors convert the plurality of words associated with each input sentence into a first vector including possible senses for the at least two words. The first vector is then combined with a second vector including a domain-specific contextual vector associated with the at least two words. The combination of the first vector with the second vector is fed into a recurrent deep logico-neural network model to generate a third vector that includes word senses for the at least two words. A threshold is set for the third vector to generate a fourth vector including a final word sense vector for the at least two words.

Abstract: To improve the technological process of computerized answering of logical queries over incomplete knowledge bases, obtain a first order logic query; with a trained, computerized neural network, convert the first order logic query into a logic embedding; and answer the first order logic query using the logic embedding.

Abstract: Method, systems, and apparatus to facilitate navigation in a known environment. Communication and tracking between a receiver device and one or more beacons are provided to identify a current position of the receiver device. A direction to a next waypoint of a current path is determined based on the identified current position and a haptic feedback system is signaled to provide continuous haptic feedback to orient a user in the identified direction.

Abstract: A signal representing a sound can be received. A machine learning model can be run to identify that the sound triggers a reaction in a user hearing the sound. A preventive action can be automatically activated to mitigate the reaction. The user's reactions can be monitored. Responsive to determining that the user's reaction has been mitigated or suppressed, the preventive action can be deactivated. The machine learning model can be retrained using at least the signal as new training data.

Abstract: Maximum expressivity can be received representing a ratio between maximum and minimum input weights to a neuron of a neural network implementing a weighted real-valued logic gate. Operator arity can be received associated with the neuron. Logical constraints associated with the weighted real-valued logic gate can be determined in terms of weights associated with inputs to the neuron, a threshold-of-truth, and a neuron threshold for activation. The threshold-of-truth can be determined as a parameter used in an activation function of the neuron, based on solving an activation optimization formulated based on the logical constraints, the activation optimization maximizing a product of expressivity representing a distribution width of input weights to the neuron and gradient quality for the neuron given the operator arity and the maximum expressivity. The neural network of logical neurons can be trained using the activation function at the neuron, the activation function using the determined threshold-of-truth.

Abstract: A media stream is delivered to a searcher by identifying a desirable emotional state for the searcher; identifying a current emotional state of the searcher; and estimating a target emotional trajectory that begins with the current emotional state and concludes with the desirable emotional state. Then the target emotional trajectory is matched to an aggregate emotional trajectory of the media stream; the media stream is recommended to the searcher in response to the matching; and a bit stream of the media stream is rendered to the searcher in response to the searcher's acceptance of the recommendation.

Abstract: Methods and systems for operating a machine learning system are described. In an example, a device can receive an image and assign a set of pixels in the image as a digital representation of a livestock. The device can further train a machine learning model using the digital representation. The device can further run the machine learning model to generate prediction data relating to the livestock. The device can further generate output data relating to at least one activity among a livestock value chain. The at least one activity can correspond to a process to generate a commodity based on the livestock.

Abstract: A contextual hashtag generation method, system, and computer program product include receiving content from an online source, identifying a set of contextual indicators for the content, determining an entity-desired outcome for the content, and generating a hashtag for the content using the set of contextual indicators while maximizing the entity-desired outcome.

Abstract: Word sense disambiguation using a glossary layer embedded in a deep neural network includes receiving, by one or more processors, input sentences including a plurality of words. At least two words in the plurality of words are homonyms. The one or more processors convert the plurality of words associated with each input sentence into a first vector including possible senses for the at least two words. The first vector is then combined with a second vector including a domain-specific contextual vector associated with the at least two words. The combination of the first vector with the second vector is fed into a recurrent deep logico-neural network model to generate a third vector that includes word senses for the at least two words. A threshold is set for the third vector to generate a fourth vector including a final word sense vector for the at least two words.

Abstract: One or more application forms can be hosted, which application forms are received from a service provider, the service provider having been authenticated by at least one data custodian of a set of data custodians. One or more application forms include at least form fields to be populated with information. A user selection of an application form to be automatically populated can be received, the user having been authenticated by at least one data custodian of the set of data custodians. Data request is sent to at least one data custodian of the set of data custodians for automatically populating at least some of the form fields. Received data from said at least one data custodian can be collated and used to populate one or more form fields. The populated form fields can be returned to the service provider, for instance, provided a minimum requirement is met.

Abstract: A signal representing a sound can be received. A machine learning model can be run to identify that the sound triggers a reaction in a user hearing the sound. A preventive action can be automatically activated to mitigate the reaction. The user's reactions can be monitored. Responsive to determining that the user's reaction has been mitigated or suppressed, the preventive action can be deactivated. The machine learning model can be retrained using at least the signal as new training data.

Abstract: Methods and systems for operating a machine learning system are described. In an example, a device can receive an image and assign a set of pixels in the image as a digital representation of a livestock. The device can further train a machine learning model using the digital representation. The device can further run the machine learning model to generate prediction data relating to the livestock. The device can further generate output data relating to at least one activity among a livestock value chain. The at least one activity can correspond to a process to generate a commodity based on the livestock.

Abstract: Method, systems, and apparatus to facilitate navigation in a known environment. Communication and tracking between a receiver device and one or more beacons are provided to identify a current position of the receiver device. A direction to a next waypoint of a current path is determined based on the identified current position and a haptic feedback system is signaled to provide continuous haptic feedback to orient a user in the identified direction.

Abstract: A system for configuring and using a logical neural network including a graph syntax tree of formulae in a represented knowledgebase connected to each other via nodes representing each proposition. One neuron exists for each logical connective occurring in each formula and, additionally, one neuron for each unique proposition occurring in any formula. All neurons return pairs of values representing upper and lower bounds on truth values of their corresponding subformulae and propositions. Neurons corresponding to logical connectives accept as input the output of neurons corresponding to their operands and have activation functions configured to match the connectives' truth functions. Neurons corresponding to propositions accept as input the output of neurons established as proofs of bounds on the propositions' truth values and have activation functions configured to aggregate the tightest such bounds.

Abstract: Maximum expressivity can be received representing a ratio between maximum and minimum input weights to a neuron of a neural network implementing a weighted real-valued logic gate. Operator arity can be received associated with the neuron. Logical constraints associated with the weighted real-valued logic gate can be determined in terms of weights associated with inputs to the neuron, a threshold-of-truth, and a neuron threshold for activation. The threshold-of-truth can be determined as a parameter used in an activation function of the neuron, based on solving an activation optimization formulated based on the logical constraints, the activation optimization maximizing a product of expressivity representing a distribution width of input weights to the neuron and gradient quality for the neuron given the operator arity and the maximum expressivity. The neural network of logical neurons can be trained using the activation function at the neuron, the activation function using the determined threshold-of-truth.

Abstract: An ontology topic is selected and a pretrained predictive language model is primed to create a predictive primed model based on one or more ontological rules corresponding to the selected ontology topic. Using the predictive primed model, natural language text is generated based on the ontology topic and guidance of a prediction steering component. The predictive primed model is guided in selecting text that is predicted to be appropriate for the ontology topic and the generated natural language text. The generated natural language text is processed to generate extracted ontology rules and the extracted ontology rules are compared to one or more rules of an ontology rule database that correspond to the ontology topic. A check is performed to determine if a performance of the ontology extractor is acceptable.