International Business Machines Corporation

Other

Kabushiki Kaisha Toshiba

Siemens Aktiengesellschaft

Nancy Anne Greco

Stephen Edward Greco

Ernest N Levine

Davide Pasetto

Jose Miguel Lobez Comeras

David Louis Harame

Kenneth Jay Stein

Joseph Thomas Kocis

Gary Robert Hueckel

Dominique Nguyen Ngoc

James Gardner Ryan

Michael F Lofaro

Stephen Larry Runyon

Tina Jane Wagner

Robert F Cook

Kenneth L DeVries

Garth A Brooks

Joan Preston

Eduardo Garcia

Anthony K Stamper

Aaron K Baughman

Arne Watson Ballantine

Jenny S Li

Kevin Shawn Petrarca

Andrew Herbert Simon

John Anthony Fitzsimmons

Giora Biran

Edward Crandal Cooney, Iii

Christopher P Ausschnitt

Erik L Hedberg

William J Cote

Darryl D Restaino

Amit Golander

Petros Zerfos

Nirmit V Desai

Heather D Achilles

Tova Roth

Ronald A Warren

Munir D Naeem

Masaki Narita

Ronald Dean Goldblatt

Oded Dubovsky

Jeffrey D Gilbert

David Alvra Wood, Iii

Luis Angel Bathen

Syed Yousaf Shah

Thomas H Ivers

Virinder Grewal

Glenn Robert Miller

Stuart M Burns

Xuan-Hong Dang

Gary William Reiss

George A Dunbar, Iii

Bruno Spuler

Adi Raz Goldfarb

Dhiraj Joshi

Gwilym Benjamin Lee Newton

Wei-Han Lee

Frank V Liucci

Eduardo Morales

Sujoy Kumar Roy Chowdhury

Cheryl Faltermeier

David H Yao

Aakash Praliya

Prakriti Pritmani

Steven Moskowitz

Parth P Dave

Kimberly F Hooper

Joseph P Nogay

Steve Greco

Satish Rajani

Shiva G

Kay Murphy

Shilpa Shenai

Arun Yashwant Ingale

Raghu Ramaswamy

Ajjay Ratnakar

John L Nard

Bruce A Root

Dynamically adjusting, using artificial intelligence (AI), sensors and models of an autonomous roaming robotic device, which includes receiving data regarding an asset at a computer of a roaming robotic device from sensors on the robotic device. The robotic device identifies an asset at a location using the sensors, and the robotic device has instructions, received from a control system, to inspect the location or items at the location. The data is analyzed using the computer of the robotic device, and the analysis includes using historical data for the asset. An AI model is loaded using the computer of the robotic device, based on the identification of the asset. A sensor is selected using the computer of the robotic device, for conducting an inspection of the asset based on the analysis of the data and the AI model.

Dynamic use of artificial intelligence (AI) models on an autonomous AI enabled robotic device

Embodiments relate to a system, program product, and method for employing deep learning techniques to fuse data across modalities. A multi-modal data set is received, including a first data set having a first modality and a second data set having a second modality, with the second modality being different from the first modality. The first and second data sets are processed, including encoding the first data set into one or more first vectors, and encoding the second data set into one or more second vectors. The processed multi-modal data set is analyzed, and the encoded features from the first and second modalities are iteratively and asynchronously fused. The fused modalities include combined vectors from the first and second data sets representing correlated temporal behavior. The fused vectors are then returned as output data.

Fusing multimodal data using recurrent neural networks

A method, computer system, and a computer program product for augmented reality guidance are provided. Device orientation instructions may be displayed as augmented reality on a display screen of a device. The device may include a camera and may be portable. The display screen may show a view of an object. At least one additional instruction may be received that includes at least one word directing user interaction with the object. The at least one additional instruction may be displayed on the display screen of the device. The camera may capture an image of the object regarding the at least one additional instruction. The image may be input to a first machine learning model so that an output of the first machine learning model is generated. The output may be received from the first machine learning model. The output may be displayed on the display screen.

Augmented reality guided inspection

An audio forecasting algorithm that is adjusted (or trained), by machine learning, prior to a sports contest that will be broadcast. The audio forecasting algorithm is then used to position a set of mobile microphones on an ongoing basis during the sports contest. In some embodiments, a band forecasting algorithm is used in the audio forecasting algorithm. In some embodiments, a swarm based correlation algorithm is used in the audio forecasting algorithm.

Forecasting sound in a live performance to determine microphone position

A computer program product is provided that includes a storage medium having instructions executable by a computer to perform a method. The method calculates, using a parse tree obtained by parsing text, a dependency graph across contextual tokens created from the text. The method generates concept instance candidates and parent-child relationships based on pattern matching and transformation of the parse tree. The method groups concept instance candidates into concept candidates and arranges the concept candidates into a tree having tree nodes. The method provides an ontology based on the tree and text and formed as an output graph of nodes. The method provides a user interface for editing the ontology by selectively adding a new node to the output graph, removing an existing node, moving a node or sub-graph across a parent-child hierarchy in the output graph, creating a new relation across the nodes, and removing an existing relation edge.

Automated ontology building

A computer-implemented method is provided for automated ontology building. The method calculates, using a parse tree obtained by parsing text, a dependency graph across contextual tokens created from the text. The method generates concept instance candidates and parent-child relationships based on pattern matching and transformation of the parse tree. The method groups concept instance candidates into concept candidates and arranges the concept candidates into a tree having tree nodes. The method provides an ontology based on the tree and text and formed as an output graph of nodes. The method provides a user interface for editing the ontology by selectively adding a new node to the output graph, removing an existing node, moving a node or sub-graph across a parent-child hierarchy in the output graph, creating a new relation across the nodes, and removing an existing relation edge.

A method and system are provided for automated ontology building. The method includes creating contextual tokens from text, parsing the text into at least one parse tree, and calculating a dependency graph across the contextual tokens using the at least one parse tree. The method further includes generating concept instance candidates and parent-child relationships based on pattern matching and transformation of the at least one parse tree. The method also includes grouping concept instance candidates into concept candidates. The method additionally includes arranging the concept candidates into a tree having tree nodes and creating predicate-based relationships between the tree nodes based on patterns and predicates identified in the text. The method further includes scoring and sorting the tree nodes. The method also includes performing an analysis of the tree nodes and rebalancing the tree based on the analysis to provide an ontology based on the text.

A novel and useful system and method of improving the utilization of a special purpose accelerator in a system incorporating a general purpose processor. In some embodiments, the current queue status of the special purpose accelerator is periodically monitored using a background monitoring process/thread and the current queue status is stored in a shared memory. A shim redirection layer added a priori to a library function task determines at runtime and in user space whether to execute the library function task on the special purpose accelerator or the general purpose processor. At runtime, using the shim redirection layer and based on the current queue status, it is determined whether to execute the library function task on the special purpose accelerator or on the general purpose processor.

Utilization of special purpose accelerators using general purpose processors

Methods and structures and methods of designing structures for charge dissipation in an integrated circuit on an SOI substrate. A first structure includes a charge dissipation ring around a periphery of the integrated circuit chip and one or more charge dissipation pedestals physically and electrically connected to the charge dissipation pedestals. The silicon layer and bulk silicon layer of the SOI substrate are connected by the guard ring and the charge dissipation pedestals. The ground distribution grid of the integrated circuit chip is connected to an uppermost wire segment of one or more charge dissipation pedestals. A second structure, replaces the charge dissipation guard ring with additional charge dissipation pedestal elements.

Methods for charge dissipation in integrated circuits

Methods for forming conductor contacts provide for etching through a capping layer located upon a conductor contact region within a substrate. A first pair of methods provide for etching through at least a lower thickness of the capping layer with other than a reactive ion etch to provide an exposed conductor contact region. A partially overlapping second pair of methods provides for converting at least an upper thickness of the capping layer to a converted material layer that is removed incident to providing an exposed conductor contact region. As adjunct to any of the methods, a liner layer is formed and located upon the exposed conductor contact region in absence of an undesirable reactive environment.

Method of making conductor contacts having enhanced reliability

A method and apparatus for cleaning a wafer with a metal exposed through an insulator, through the use of a wet cleaning tank in concert with a feedback system on the potential difference between two leads of the wet cleaning tank. The cleaning tank has a bath in which the wafer and the two leads are immersed. The potential difference between the two leads is regulated when the feedback system detects a change in the potential across the two leads.

Method and apparatus for copper corrosion prevention during wet clean

Method and structure for charge dissipation in integrated circuits

Custom connections between pairs of copper wires in a last damascene wiring level are effected by creating openings in an overlying insulating layer which span a distance between portions of the two wires, then filling the openings with aluminum. The openings can be created (or completed) by a second, maskless UV laser exposure of positive photoresist which is used for patterning the insulating layer. If an opening is not created, an aluminum connecting shape overlying the insulating layer will not effect a connection between the two wires. Similar results can be achieved by laser exposure of a resist used to pattern the aluminum layer, thereby causing breaks in connecting shape when it is desired not to have a connection.

Customizing back end of the line interconnects

An interconnection wiring system incorporating two levels of interconnection wiring separated by a first dielectric, a capacitor formed by a second dielectric, a bottom electrode of the lower interconnection wiring or a via and a top electrode of the upper interconnection wiring or a separate metal layer. The invention overcomes the problem of leakage current and of substrate stray capacitance by positioning the capacitor between two levels of interconnection wiring.

Metal-insulator-metal capacitor

Growing community of inventors

Lagrangeville, NY, United States of America

Nancy Anne Greco