International Business Machines Corporation

Senthil Kumar Kumarasamy Mani

Srikanth Govindaraj Tamilselvam

Vibha Singhal Sinha

Pankaj Dhoolia

Sampath Dechu

Neelamadhav Gantayat

Shreya Khare

Rahul Aralikatte

Giriprasad Sridhara

Anush Sankaran

Naveen Panwar

Rohan Raju Padhye

Vijay Ekambaram

Saurabh Sinha

Pratyush Kumar

Maja Vukovic

Jinho Hwang

Sameep Mehta

Anup Kalia

Kalapriya Kannan

John Joseph Rofrano

Jin Xiao

Monika Gupta

Parag Jain

Tarun Tater

Utkarsh Milind Desai

Saravanan Krishnan

Sai Koti Reddy Danda

Malik Jackson

Tanmayee Narendra

Methods, systems, and computer program products for factchecking artificial intelligence models using blockchain are provided herein. A computer-implemented method includes obtaining at least one artificial intelligence model and at least one set of data related to the at least one artificial intelligence model; determining a set of characteristics based at least in part on the at least one artificial intelligence model and the at least one set of data; selecting one of a plurality of networks based at least in part on a target deployment of the at least one artificial intelligence model to verify the set of characteristics; generating a report based at least in part on verifying the set of characteristics using the selected network, wherein the report establishes a threshold level of trust for the at least one artificial intelligence model; and storing the report on a blockchain.

Factchecking artificial intelligence models using blockchain

A method, computer system, and a computer program product for debugging a deep neural network is provided. The present invention may include identifying, automatically, one or more debug layers associated with a deep learning (DL) model design/code, wherein the identified one or more debug layers include one or more errors, wherein a reverse operation is introduced for the identified one or more debug layers. The present invention may then include presenting, to a user, a debug output based on at least one break condition, wherein in response to determining the at least one break condition is satisfied, triggering the debug output to be presented to the user, wherein the presented debug output includes a fix for the identified one or more debug layers in the DL model design/code and at least one actionable insight.

Debugging deep neural networks

One embodiment provides a method, including: mining a plurality of deep-learning models from a plurality of input sources; extracting information from each of the deep-learning models, by parsing at least one of (i) code corresponding to the deep-learning model and (ii) text corresponding to the deep-learning model; identifying, for each of the deep-learning models, operators that perform operations within the deep-learning model; producing, for each of the deep-learning models and from (i) the extracted information and (ii) the identified operators, an ontology comprising terms and features of the deep-learning model, wherein the producing comprises populating a pre-defined ontology format with features of each deep-learning model; and generating a deep-learning model catalog comprising the plurality of deep-learning models, wherein the catalog comprises, for each of the deep-learning models, the ontology corresponding to the deep-learning model.

Deep-learning model catalog creation

Techniques for the suggestion and completion of deep learning models are disclosed including receiving a set of data and determining at least one property of the data. A plurality of characteristics of a computing device and a plurality of deep learning models are received and a score for each of the plurality of deep learning models is determined based on the received computing device characteristics and the determined at least one property of the data. The plurality of deep learning models are ranked for presentation to a user based on the determined scores. One or more of the deep learning models are presented on a display based on the ranking. A selection of one of the deep learning models is received and the selected deep learning model is trained using the set of data.

Suggestion and completion of deep learning models from a catalog

Systems and techniques that facilitate automated recommendation of microservice decomposition strategies for monolithic applications are provided. In various embodiments, a community detection component can detect a disjoint code cluster in a monolithic application based on a code property graph characterizing the monolithic application. In various aspects, the code property graph can be based on a temporal code evolution of the monolithic application. In various embodiments, a topic modeling component can identify a functional purpose of the disjoint code cluster based on a business document corpus corresponding to the monolithic application. In various embodiments, a microservices component can recommend a microservice to replace the disjoint code cluster based on the functional purpose.

Microservice decomposition strategy of monolithic applications

Methods, systems, and computer program products for assisting dependency migration are provided herein. A computer-implemented method includes determining differences between a first version of a dependency used by a software application and each of a plurality of upgrade candidates, the plurality of upgrade candidates comprising at least one of: (i) one or more newer versions of the dependency and (ii) a substitute dependency; identifying, based on the determined differences for a given one of the upgrade candidates, one or more sections of code of the software application that need to be patched in order to be compatible with the given upgrade candidate; and generating a modified version of the software application for the given upgrade candidate that comprises one or more patches for at least a portion of the identified one or more sections of code.

Assisting dependency migration

Methods, systems and computer program products for natural language context embedding are provided herein. A computer-implemented method includes extracting a document anatomy and document elements from a given structured document, identifying semantic references in the given structured document, and generating an ontology comprising (i) a hierarchy of concepts and (ii) relations connecting the concepts, each concept comprising attributes for a document element. The computer-implemented method also includes generating natural language text context for a given document element by utilizing the ontology to combine (i) attributes of a given concept corresponding to the given document element with (ii) attributes of another concept, the other concept corresponding to another document element, the other concept being connected to the given concept by at least one relation. The computer-implemented method further includes modifying the given structured document by embedding the natural language context with the given document element in the given structured document.

Embedding natural language context in structured documents using document anatomy

Embodiments of the present invention provide a method, a computer program product, and a system for generating a haptic signal representing a fabric composition. Embodiments of the present invention can be used to generate a haptic signal that is based on a user selection. For example, embodiments of the present invention can combine characteristic signals corresponding to a plurality of textiles to generate the haptic signal for output to a haptic device. Embodiments of the present invention can be used to recommend similar fabric compositions based upon similarity between a characteristic signal of a fabric composition and the haptic signal.

Simulating tactile information for haptic technology

Embodiments describe an approach for automatically generating feedback for an online forum. Embodiments determine if a user is using a solution to a problem, wherein the solution is posted on an online forum, and responsive to determining the user is using the solution, capturing environment information associated with the user's computing device. Additionally, embodiments determine if the solution solved the problem, and responsive to determining the solution solved the problem, automatically generate feedback associated with the solution, wherein the feedback comprises the environment information and information detailing that the solution solved the problem.

Online forum automated feedback generator

One embodiment provides a method, including: receiving input of a learning session that is being conducted by an educator, being provided to at least one user, and being related to a subject; determining, using a knowledge base, that at least one topic relevant to the subject of the learning session is incomplete, wherein the determining comprises building a knowledge subgraph of the learning session and comparing the built knowledge subgraph to at least a portion of the knowledge base; generating at least one question to be asked of the educator relevant to the at least one incomplete topic; identifying, using at least one natural language text classifier model, a location within the learning session to ask the generated at least one question; and providing, to the educator, an output corresponding to the at least one question at the identified location within the learning session.

Question generation for learning session

One embodiment provides a method, including: utilizing at least one processor to execute computer code that performs the steps of: using an electronic device to engage in an interactive session between a user and a virtual assistant; receiving, at the electronic device, audio input from the user, wherein the audio input comprises a problem-solving query corresponding to a request by the user for assistance in solving a problem related to at least one object; parsing the audio input to identify at least one annotated video file corresponding to the at least one object and the problem-solving query; determining a state of the object and a location in the at least one annotated video file corresponding to the state of the object; and providing, to the user and based on the location in the at least one annotated video file, instructional output related to the problem-solving query.

Interactive voice based assistant for object assistance

One embodiment provides a method, including: receiving a natural language query; selecting a disambiguation state model representing conversational dialog history, wherein the disambiguation state model comprises a plurality of nodes representing an entity, and a plurality of edges representing a path between two of the plurality of nodes, each of the plurality of edges including an assigned weight; traversing, the disambiguation state model using the natural language query to select a path to one of the plurality of nodes and providing the user the entity associated with the one of the plurality of nodes and iteratively selecting paths and nodes based upon input received from the user until a final node of the disambiguation state model is reached; providing a response to the natural language query based upon the entity of the final node; and updating the disambiguation state model based upon the traversed paths and nodes.

Adaptive conversational disambiguation system

A mobile application update manager functioning on a user device defers a new update for a mobile application for a first time period. The mobile application update manager predicts a time and size of a next update for the mobile application, a set of changes associated with the new update, and a relevancy of the set of changes to a user of the user device. The mobile application update manager recommends if the new update should be implemented or if the user should defer until a next update is available for the mobile application.

Mobile application update manager

One embodiment provides a method, including: tracking behavior of a user when the user is providing input to a permission request of an application, wherein the permission request comprises at least one application permission requesting access for the application to information accessible by an information handling device; identifying at least one undesired application permission, wherein the identifying comprises detecting, based upon the behavior of the user, that the user is uncomfortable with the at least one undesired application permission; determining whether another similar application, having a permission set the user is comfortable with, is available, wherein the determining comprises searching for applications similar to the application and filtering the similar applications by removing applications having a permission similar to the undesired application permission; and providing a recommendation, if there is another similar application, to the user, wherein the recommendation comprises the another similar application.

Application recommendation based on permissions

Methods, systems and computer program products are disclosed for controlling generation of change notifications to the one or more users in a collaborative authoring environment. An automated mechanism is provided to detect the change performed in the artifact. The one or more users who performed changes in the past with the changed artifact are identified. One or more pre-defined parameters, such as contribution, ownership, recency, and longevity, may be used to compute relevancy of the changes made in the changed artifact to determine the qualifying one or more users to be notified. Notifications are generated and delivered to the one or more qualifying other users assessed on the one or more pre-defined parameters.

Growing community of inventors

Bengaluru, India

Senthil Kumar Kumarasamy Mani