International Business Machines Corporation

Micah Forster

Aaron K Baughman

Sai Krishna Reddy Gudimetla

Craig M Trim

Stephen Carl Hammer

Sarbajit Kumar Rakshit

Shikhar Kwatra

Garfield Winston Vaughn

Gray Franklin Cannon

Kavitha Hassan Yogaraj

John Coleman Newell

Corey B Shelton

Gururaja Hebbar

Eduardo Morales

Yoshika Chhabra

Hernan A Cunico

Paul A R Frank

Mohit Trivedi

Sidhartha Balodi

Using a model executing on a classical processor, a set of classical features is scored. The scored set of classical features is divided into a set of feature groups, a number of classical features in a group determined according to a qubit capability of a quantum processor. Using a model executing on the quantum processor and a group of the scored set of classical features, a set of quantum features is scored. The score of a quantum feature is adjusted according to an accuracy of the quantum data model. The scored set of classical features and the scored set of quantum features are combined according to a measure of differences between the scored set of classical features and the scored set of quantum features. Using the combined set of scored features and a first set of input data of a resource, a valuation of a resource is calculated.

Combined classical/quantum predictor evaluation with model accuracy adjustment

Using a classical data model executing on a classical processor, a set of classical features is scored. A score of a classical feature comprises an evaluation of a utility of the classical feature in predicting a result involving a resource. Using a quantum data model executing on a quantum processor and the scored set of classical features, a set of quantum features is scored. The quantum data model is executed a number of times previously determined using a set of results of executing the quantum data model on a set of annotated training data. The scored set of classical features and the scored set of quantum features are correlated, forming a combined set of scored features. Using the combined set of scored features and a first set of input data of a resource, a valuation of the resource is calculated.

Identifying related messages in a natural language interaction in multiple iterations

An embodiment of the invention may include a method, computer program product, and computer system for managing a machine learning algorithm. The embodiment may include a computing device that distributes a first algorithm to a plurality of computing devices. The embodiment may include updates to the first algorithm, to create a second algorithm, by a first device of the plurality of computing devices. The first device is grouped with other devices in a first cluster of devices of the plurality of computing devices. The first cluster of computing devices comprises more than one computing device. Updating the first algorithm is performed based on information shared amongst the first cluster of devices.

Sharing and executing custom machine learning algorithms

Methods, computer program products, and systems are presented. The methods can include, for instance: generating a plurality of deep transfer learning networks. Further, the methods can include, for instance: encoding one or more transfer layers.

Transfer learning based on cross-domain homophily influences

Using a logistic regression classification model executing on a processor, a topic is classified into an interaction type in a set of predefined interaction types. A set of documents corresponding to the topic is extracted from a document repository. Using a generative adversarial model executing on a processor, a sentiment corresponding to a reaction to a previous presentation is scored, the scoring resulting in a scored sentiment. Using a trained attention layer model, the interaction type, the set of documents, and the scored sentiment are weighted, the weighting generating a weighted interaction type, a weighted set of documents, and a weighted scored sentiment. Using a natural language generation transformer model executing on the processor, a document in the weighted set of documents is weighted according to the weighted interaction type and the weighted scored sentiment.

Automated document adaptation based on topic classification

A computer-implemented method and system for autonomic cloud to edge compute allocations in a sports fantasy league trade transaction. The computer implemented method includes, in one embodiment, calculating, based on an expected return associated with each player on each of a plurality of teams in a fantasy sports league, a valuation for each player. An embodiment includes determining a positional need for each of the plurality of teams in the fantasy sports league, and determining, based on the valuation for each player and the positional need for each team, one or more players to include in a trade with another team of the plurality of teams.

Autonomic cloud to edge compute allocation in trade transactions

An embodiment includes accessing captured video of a first physical object in a physical environment. The embodiment also includes detecting a feature of the first physical object in a first frame of the video. The embodiment encodes a first qubit with a first quantum state based on a first value of the feature of the first physical object, and then entangles the first qubit with a second qubit forming an entangled qubit pair. The embodiment detects a second quantum state of the second qubit of the entangled qubit pair and renders computer-generated content of a virtual environment that includes a computer-generated first virtual object that corresponds to the first physical object, where the rendering comprises determining a property of the first virtual object based on the detected second quantum state.

Synchronizing physical and virtual environments using quantum entanglement

A computer-implemented method, a computer system and a computer program product refine service inquiries through an understanding of user context. The method includes receiving a service inquiry from a user on a computing device. The method also includes capturing movement data within a user environment. The movement data is selected from a group consisting of audio data, video data and telemetry data extracted from a second device in the user environment. The method further includes determining a user context by correlating motion and position of the user with respect to the user environment. In addition, the method includes generating a set of predicted modifications to the service inquiry based on the user context. Lastly, the method includes displaying the set of predicted modifications to the service inquiry on the computing device.

Contextual enhancement of user service inquiries

Using a first trained generative adversarial network, a first multimedia content is transformed into a text description of the first multimedia content. The text description is adjusted according to a constraint using a trained attention layer, the adjusting creating an adjusted text description. Using a trained model, the adjusted text description is transformed into a second multimedia content, the second multimedia content comprising an adjustment of the first multimedia content according to the constraint.

Automated multimodal adaptation of multimedia content

Simulating uncertainty in an artificial neural network is provided. Aleatoric uncertainty is simulated to measure what the artificial neural network does not understand from sensor data received from an object operating in a real-world environment by adding random values to edge weights between nodes in the artificial neural network during backpropagation of output data of the artificial neural network and measuring impact on the output data by the added random values to the edge weights between the nodes. Epistemic uncertainty is simulated to measure what the artificial neural network does not know by dropping out a selected node from each respective layer of the artificial neural network during forward propagation of the sensor data and measuring impact of dropped out nodes on the output data of the artificial neural network. An action corresponding to the object is performed based on the impact of simulating the aleatoric and epistemic uncertainty.

Epistemic and aleatoric deep plasticity based on sound feedback

Methods, computer program products, and systems are presented. The methods include, for instance: generating a plurality of deep transfer learning networks including a source deep transfer learning network for a source domain and a target deep transfer learning network for a target domain. Transfer layers of the source deep transfer learning network are encoded to a chromosome, diversified, and integrated with the target deep transfer learning network and the target deep transfer learning network passing a predefined fitness threshold condition is produced.

A processor may monitor frequency data related to a user metric of a user during a measurement window. The user metric may relate to the user's use of a computer implemented environment. The processor may simplify the frequency data related to the user metric, resulting in a set of simplified frequency data. The processor may input the set of simplified frequency data into a neural network. The neural network may determine a likelihood of a negative user experience for the user. The processor may alter a parameter of the first user environment based on the likelihood.

Growing community of inventors

Round Rock, TX, United States of America

Micah Forster