International Business Machines Corporation

John Thomas Richards

Rachel K E Bellamy

Peter Kenneth Malkin

Calvin Bruce Swart

Sharon Mary Trewin

Jacquelyn Annette Martino

Paul Michael Matchen

Michael Desmond

Stephanie Houde

John C Thomas, Jr

Bonnie E John

Wendy Anne Kellogg

David John Piorkowski

Luis Alfonso Lastras-Montano

Michele M Franceschini

Philip Shilung Yu

Mark N Wegman

Thomas David Erickson

Livio B Soares

James Edward Christensen

Harold Leon Ossher

Qingzi Vera Liao

Rachel Katherine Emma Bellamy

Justin David Weisz

Steven I Ross

Jason Benjamin Ellis

Yunfeng Zhang

William Edward Bennett

Fernando Carlos Martinez

Mark Richard Laff

Michael Muller

Sameep Mehta

Robert G Farrell

Ramya Raghavendra

Samuel Scott Adams

Kalapriya Kannan

Evelyn Duesterwald

Kush Raj Varshney

Aleksandra Mojsilovic

Darrell Christopher Reimer

Manish Kesarwani

Matthew R Arnold

Clay Edwin Williams

Tracee L Wolf

Kaoutar El Maghraoui

Michael James Hind

Kartik Talamadupula

Vicki Lynne Hanson

Mayank Agarwal

Jason Tsay

Margaret Myers Burnett

Jonathan P Brezin

Lewis Alexander Morrow

Rachel Ke Bellamy

Rhonda Rosenbaum

David John Pirokowski

Rachel Katherine Emma Ballamy

Austin Zachary Henley

Joseph A Lawrance

An autonomous agent operating method, system, and computer program product, including launching a first autonomous agent for a task with an initial update interval and adjusting the initial update interval for a second autonomous agent based on a second task for the second autonomous agent being similar to the task over time in relation to a trust level of a human user in a performance of the first autonomous agent.

Increasing trust formation and reduce oversight costs for autonomous agents

Performance of a computer implementing a machine learning system is improved by providing, via a graphical user interface, to an annotator, unlabeled corpus data to be labeled; obtaining, via the interface, labels for the unlabeled corpus data; and detecting, with a consistency calculation routine, concurrent with the labeling, internal inconsistency and/or external inconsistency in the labeling. Responsive to the detection, intervene in the labeling with a reactive intervention subsystem until the inconsistency is addressed. The labeling is completed subsequent to the intervention; the system is trained to provide a trained machine learning system, based on results of the completed labeling; and classification of new data is carried out with the trained system. Proactive intervention schemes are also provided.

Framework of proactive and/or reactive strategies for improving labeling consistency and efficiency

Embodiments relate to interactive graphical display. A request is processed by a generative system to generate multiple hypotheses of an output in response to the request, a primary hypothesis of the multiple hypotheses having a highest confidence for the output, multiple secondary hypotheses of the multiple hypotheses having a lower confidence than the highest confidence. At least one region of divergence is determined from the primary hypothesis by the multiple secondary hypotheses, the at least one region of divergence having alternatives in the multiple secondary hypotheses, the alternatives in the multiple secondary hypotheses differing from the primary hypothesis. A graphical user interface displays the at least one region of divergence in the primary hypothesis and alternatives in the multiple secondary hypotheses for the at least one region of divergence, the alternatives and primary hypothesis for the at least one region of divergence being displayed as selectable options for a user.

Interactive graphical display of multiple overlapping hypotheses or document versions

An autonomous agent operating method, system, and computer program product, including configuring an autonomous agent for a task, launching the autonomous agent with an initial update interval, the update interval determining a frequency of the autonomous agent reporting results to a human user for review, measuring the trust level of human user in a performance of the autonomous agent, and dynamically adjusting the update interval based on this measured trust.

A method of using artificial intelligence to provide source code from an original programming language in a target programming language showing regions of low confidence. The method includes receiving, by a computing device, a code base in an original programming language. The computing device further provides the code base in the original programming language to a target programming language using an artificial intelligence tool. The computing device additionally displays the code base in the target programming language using a visualization tool in a visual interface. The computing device still further displays the regions of uncertainty to a human user in the visual interface. The regions of uncertainty provide low confidence regions of the code base in the target programming language for targeted user intervention. The regions of low confidence correlate with violations to provide displayed actionable insight regions.

Computer assisted programming with targeted visual feedback

A method, a computer program product, and a computer system determine when to transfer a communication session from an agent to a bot. The method includes monitoring the communication session between the agent and a user. The method includes determining a continuing utility value indicating a predicted continuing cost to maintaining the communication session with the agent. The continuing utility value is indicative of a predicted continuing benefit to maintaining the communication with the agent. The method includes determining a transferring utility value indicating a predicted transferring cost to transferring the communication session from the agent to the bot. The transferring utility value is indicative of a predicted transferring benefit to transferring the communication session from the agent to the bot. The method includes, as a result of the predicted transferring benefit being greater than the predicted continuing benefit, transferring the communication session from the agent to the bot.

Agent to bot transfer

A method for automatically generating documentation for an artificial intelligence model includes receiving, by a computing device, an artificial intelligence model. The computing device accesses a model facts policy that indicates data to be collected for artificial intelligence models. The computing device collects artificial intelligence model facts regarding the artificial intelligence model according to the model facts policy. The computing device accesses a factsheet template. The factsheet template provides a schema for an artificial intelligence model factsheet for the artificial intelligence model. The computing device populates the artificial intelligence model factsheet using the factsheet template with the artificial intelligence model facts related to the artificial intelligence model.

Generation and management of an artificial intelligence (AI) model documentation throughout its life cycle

According to an aspect, searching, recommending, and exploring documents through conceptual associations includes a method for receiving a plurality of documents and extracting concepts from each of the documents. A degree of relation between each of the documents and concepts in a knowledge base is calculated. The method also includes, in response to receiving a query, determining one or more concepts from the query. For each of the concepts, a list of documents having a highest degree of relation to the concept is retrieved. The method also includes outputting a list that is responsive to the one or more retrieved lists.

System for searching, recommending, and exploring documents through conceptual associations

According to an aspect, searching, recommending, and exploring documents through conceptual associations includes receiving a plurality of documents and extracting concepts from each of the documents. A degree of relation between each of the documents and concepts in a knowledge base is calculated. An aspect also includes, in response to receiving a query, determining one or more concepts from the query. For each of the concepts, a list of documents having a highest degree of relation to the concept is retrieved. An aspect also includes outputting a list that is responsive to the one or more retrieved lists.

Detecting user input based on multiple gestures is provided. One or more interactions are received from a user via a user interface. An inferred interaction is determined based, at least in part, on a geometric operation, wherein the geometric operation is based on the one or more interactions. The inferred interaction is presented via the user interface. Whether a confirmation has been received for the inferred interaction is determined.

Detecting input based on multiple gestures

Systems and methods are provided for post-hoc correction of calibration errors in eye tracking data, which take into consideration calibration errors that result from changes in user position during a user session in which the user's fixations on a display screen are captured and recorded by an eye tracking system, and which take into consideration errors that occur when the user looks away from a displayed target item before selecting the target item.

Correcting systematic calibration errors in eye tracking data

Growing community of inventors

Chappaqua, NY, United States of America

John Thomas Richards