International Business Machines Corporation

Dorothea W Wiesmann Rothuizen

Birgit Monika Pfitzmann

Mark Alfred Lantz

Thomas R Albrecht

Jinho Hwang

Larisa Shwartz

Urs T Duerig

Hugo Eric Rothuizen

Michel Despont

Rafal Bigaj

Frank Bagehorn

Amol Bhaskar Mahamuni

Marcos Vinicius L Paraiso

Vidhya Shankar Venkatesan

Honglei Guo

Changhua Sun

Lynette Yvonne Mitchell

Brent Alan Goebel

Elizabeth Whittum Byrd

Herve Durand

Systems, computer-implemented methods, and computer program products that can facilitate refinement of a predicted event based on explainability data are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an interpreter component that identifies a probable cause of a predicted event based on explainability data. The computer executable components can further comprise an enrichment component that executes a diagnostic analysis based on the probable cause.

Refinement of a predicted event based on explainability data

In an approach for automatically extracting product baseline information from a request for proposal document, a processor receives the document. A processor detects a table in the document. A processor identifies a table header on the table. The table header is associated with a name and an associated volume of the product. A processor extracts context based on the table header from the table. The context includes the name and the associated volume of the product. A processor maps the extracted context with the name of the product in the table to an associated name of the product based on a pre-defined product ontology.

Product baseline information extraction

A method, a computer system, and a computer program product for managing a dataset of training samples, labeled by class, during training of a machine learning model is provided. Embodiments of the present invention may include training the model on a sequence of increasing-sized sets of the training samples and testing performance of the model after training with each set to obtain class-specific performance metrics corresponding to each set size. Embodiments of the present invention may include generating class-specific learning curves from the performance metrics for the plurality of classes. Embodiments of the present invention may include extrapolating the learning curves. Embodiments of the present invention may include optimizing a function of the predicted performance metrics to identify a set of augmentation actions to augment the dataset for further training of the model. Embodiments of the present invention may include providing an output indicative of the set of augmentation actions.

Dataset management in machine learning

Computer-implemented methods and systems are provided for identifying IT service compositions corresponding to subsets of a set R of IT service requirements. Such a method includes providing a data structure including, for a set S of IT services, a master graph having master nodes representing respective subsets of like services in S, interconnected by master edges each representing an integration-need between nodes interconnected by that edge. The method further comprises, for each service composition being a set of services, integrated by integration components and spanning all master nodes, in the composition subgraph, comparing the composite attributes of services and integration components in that composition with the requirements in R' to select at least one preferred service composition for R&#x2032;, and outputting composition data defining each preferred service composition.

Automated information technology services composition

A data storage device comprises a storage medium for storing data in the form of marks and at least one probe for scanning the storage medium. The storage medium may be comprised in a substrate. The probe comprises a cantilever that comprises terminals serving as electrical contacts an being during operation of the probe mechanically fixed to a probe-holding structure, which may be a common frame of the data storage device. A probe further comprises a supporting structure, to which the terminals are mechanically directly coupled or coupled via hinges and which extends away from the terminals. A tip with a nanoscale apex is provided. A beam structure comprises a heating resistor and is attached at ends to the supporting structure. The beam structure is thinned at least in a direction parallel to an axis of the tip compared to an area of the supporting structure abutting the beam structure.

Probe for scanning over a substrate and data storage device

Probe for scanning over a substrate and a data storage device

Growing community of inventors

Adliswil, Switzerland

Dorothea W Wiesmann Rothuizen