International Business Machines Corporation

Kyndryl, Inc.

Wayfair LLC

Nuance Communications, Inc.

Airbnb, Inc.

Daedalus Blue LLC

Aaron K Baughman

Mauro Marzorati

Brian M O'Connell

Shikhar Kwatra

Craig M Trim

Stephen Carl Hammer

Todd Russell Whitman

Diwesh Pandey

Gray Franklin Cannon

Nicholas Albert McCrory

Gary Francis Diamanti

Peter Kenneth Malkin

Barry Michael Graham

Christian Eggenberger

Micah Forster

Sarbajit Kumar Rakshit

John P Perrino

David C Bastian

James R Kozloski

Thomas Benjamin Harrison

Mohamed Nooman Ahmed

Christopher J Dawson

Martin G Keen

Garfield Winston Vaughn

Palani Sakthi

Rick A Hamilton, Ii

John F Behnken

Herbert Daniel Pearthree

Brian James Snitzer

Christopher Eythan Holladay

Ahmed M Nassar

Jeremy R Fox

John Michael Ganci, Jr

Michael Bender

Hernan A Cunico

Raghuveer Prasad Nagar

Timothy Michael Lynar

John Michael Wagner

Mary E Rudden

Clifford A Pickover

Vijay Ekambaram

Cesar Augusto Rodriguez Bravo

Sathya Santhar

Blaine H Dolph

Malolan Chetlur

Jeffrey David Amsterdam

Aditya Anand Kalyanpur

Linda M Boyer

Marc Yvon

Gregory J Boss

Valentina Salapura

Kulvir Singh Bhogal

Gandhi Sivakumar

Dong Chen

Charles Evan Beller

Marco Aurelio Stelmar Netto

Qiqing Christine Ouyang

Robert G Farrell

Aaron Roger Cox

Kimberly Greene Starks

Louis Bennie Capps, Jr

Tiberiu (Jim) Suto

Boaz Mizrachi

Arun Joseph

Michael Man Behrendt

Brenda Lynn Dietrich

David W Buchanan

Oded Dubovsky

James Edward Bostick

Fang Lu

Zachary A Silverstein

John David Wilson

Joseph N Kozhaya

Vinod A Valecha

Hemant Kumar Sivaswamy

Brian Paul Gaucher

Sreekanth Ramakrishna Iyer

Nader M Nassar

Rudolf Maarten Bolle

Smitkumar Narotambhai Marvaniya

Prasenjit Dey

Guillermo A Cecchi

Uri Kartoun

James J Fan

Vagner Figueredo De Santana

Brian Frederick Ober

Victor Povar

Natalie Brooks Powell

Gopal Sarma Pingali

Nancy Anne Greco

Ann Corrao

Phani Kumar V U Ayyagari

Indervir Singh Banipal

William G Dubyak

Sherif Ahmed Goma

Madan K Chukka

Yaser K Doleh

Guy Feigenblat

Tamer M Nassar

Utpal Mangla

An example operation may include one or more of executing queries on one or more external data stores to retrieve domain data of one or more ranked lists of assets and variables corresponding to the domain data, generating a plurality of feature groups based on the retrieved domain data and variables, wherein the plurality of feature groups correspond to a plurality of features used to generate the one or more ranked lists, converting the plurality of features groups into a plurality of values via execution of an optimization engine, transforming the plurality of values into a plurality of sentences describing the plurality of feature groups, and displaying the plurality of sentences via a user interface.

Generation of reasoning for asset rankings

Creating movement in a physical environment includes extracting, by computer hardware, digital features from interactions of a user with a digital environment that models a physical environment. Physical features are extracted by the computer hardware from sensor data generated from detected interactions of the user with the physical environment. A recommendation is generated by the computer hardware for the user within the physical environment based on a correlation of the digital features with the physical features. The recommendation is provided to the user. Providing the recommendation may include generating haptic signals by decoding, using a decoder stage executed by the computer hardware, the physical features and the recommendation, wherein the haptic signals specify a movement of the user within the physical environment in furtherance of the recommendation.

Generative artificial intelligence system for creating movement in a physical environment

An embodiment includes selecting, using a first attribute of a first object, the first object in a first volumetric video. The embodiment also includes selecting, using a second attribute of a second object, the second object in a second volumetric video, where the first attribute and the second attribute satisfy an aggregation rule. The embodiment also includes generating an aggregated volumetric video from the first volumetric video and the second volumetric video, where the generating of the aggregated video comprises rendering the first object and the second object simultaneously in the aggregated volumetric video based on the aggregation rule.

Personalized aggregation of volumetric videos

Using a probability distribution and a search result history, a probability of selecting a specified number of relevant samples and a specified number of irrelevant samples from a set of contents is computed, each content in the set of contents comprising a content copied to a first system clipboard of a first device. Using the probability distribution, each content in the set of contents is weighted. Using the weighted set of contents, a set of predicted searches is generated. The set of predicted searches is presented for selection responsive to an indication of intent to perform a search. A selected search within the set of predicted searches is caused to be performed.

Clipboard based search term prediction

An embodiment senses a sequence, responsive to the sensed sequence, segments the sensed sequence into a prompt and text. The embodiment generates an attention embedding representative of the text and computes an attention weight based on the attention embedding. The embodiment generates a prompt embedding representative of the prompt. The embodiment computes a relationship between the prompt embedding and the attention weight comprising correlating the attention embedding and the attention weight based on a beam search; bin packing the prompt embedding where a bin is defined by the attention embedding; matching the prompt embedding to the bin based on a Minkowski distance metric; where the bin packing causes the computing of the relationship between the prompt and the text represented by the attention weight.

Prompt discovery with attention refinement

From a first model parameter, an autoencoder network is generated. A reconstruction error for the autoencoder network is measured, the reconstruction error comprising a difference between an input to the autoencoder network and a corresponding output from the autoencoder network, the input to the autoencoder network comprising a portion of an initial set of data. The reconstruction error and a confidence score corresponding to a complexity level of the autoencoder network are aggregated into a level of difficulty score of the autoencoder network. From the level of difficulty score and an initial data access policy level corresponding to the initial set of data, a derived data access policy level corresponding to the initial data access policy level is generated, the derived data access policy level enforcing access to a transformed set of data generated by applying a transformation to the initial set of data.

Automatically adjusting data access policies in data analytics

Providing a hybrid neural network architecture by training a plurality of models using a set of training data, the plurality comprising quantum models and classical models, evaluating each model using a common test data set, assigning one or more evaluation metrics to each model according to the evaluation, generating a plurality of networks, each network comprising a combination of the models, evaluating a flow of each network, selecting a network according to the flow, and providing the selected network to a user.

Generating hybrid quantum-classical neural network architectures

The illustrative embodiments provide for adaptation of reference architecture documents across clouds. An embodiment includes loading a reference architecture document. The embodiment also includes populating a knowledge repository corpus where the knowledge repository corpus includes data from information technology (IT) products, cloud services, and integrations stored with associated metadata about functionalities. The IT products, the cloud services, and the integrations are stored with metadata. The embodiment also includes classifying, using an incident analysis module, the service incidents based on the reference architecture document. The embodiment also includes detecting flaws in the reference architecture document based on the classified service incidents. The embodiment also includes creating a weighted graph of the cloud services. The embodiment also includes traversing the weighted graph and creating an adapted reference architecture based on the traversed weighted graph.

Adaptation of reference architecture documents across clouds

A computer-implemented method for orchestrating operation of multiple vehicles includes generating a single display image stream based on multiple image streams, each image stream corresponding to a respective vehicle, the vehicles being assigned to be controlled by a remote operating client. The method further includes receiving, from the remote operating client, a vehicle operation instruction in response to the single display image stream being displayed by the remote operating client. The method further includes transmitting, to at least one vehicle from the multiple vehicles, the operation instruction to manipulate operation of the at least one vehicle.

Orchestrating vehicles and remote operating clients

By analyzing a natural language content concurrently with a presentation of the natural language content, a first language of the natural language content is detected. By analyzing the natural language content concurrently with the presentation of the natural language content, it is detected that a subset of the natural language content is expressed in a second language, wherein the second language is different from the first language, wherein a set of known languages comprises the first language, wherein the set of known languages excludes the second language. From the subset of the natural language content, a modified subset expressed in the first language is generated. The modified subset is inserted into the natural language content.

Contextual and personalized real time content modification for language assistance

Using a classical data model executing on a classical processor, a set of classical features is scored. A classical feature comprises a first attribute of a resource, and a score of the classical feature comprises an evaluation of a utility of the classical feature in predicting a result involving the 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 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.

Combined classical/quantum predictor evaluation

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

An embodiment includes identifying, from among the plurality of digital content datasets, a set of candidate textual items based on relevance to a specified subtopic using one or more natural language processing techniques. The embodiment groups candidate textual items into a predetermined number of groups using relevance scores and feature vectors. The embodiment trains a pre-trained encoder-decoder model using a designated group of selected textual items, where the pre-trained encoder-decoder model is pretrained to generate textual content according to a particular style of writing. The embodiment generates, using the pre-trained encoder-decoder model, machine-authored textual content in the particular style of writing resulting in an article about the specified subtopic based on the designated group of selected textual items. The embodiment also includes transmitting the article to a remote web server as an update for a website.

Elucidated natural language artifact recombination with contextual awareness

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

Growing community of inventors

Cary, NC, United States of America

Aaron K Baughman