International Business Machines Corporation

Rachel Brill

Ryan Thomas Rawlins

Dale E Blue

Andrew C Hicks

Aviad Zlotnick

Eitan D Farchi

Orna Raz

Deborah A Furman

A method, apparatus and a computer program product for automated data slicing based on an Artificial Neural Network (ANN). The method comprising: obtaining an ANN, wherein the ANN is configured to provide a prediction for a data instance, wherein the ANN comprises a set of nodes having interconnections therebetween; determining an attribute vector based on a subset of the nodes of the ANN; determining, based on the attribute vector, a plurality of data slices; obtaining a testing dataset comprising testing data instances; computing, for each data slice, a performance measurement of the ANN over the data slice, wherein said computing is based on an application of the ANN on each testing data instance that is mapped to the data slice; and performing an action based on at least a portion of the performance measurements of the data slices.

Automated data slicing based on an artificial neural network

A method and a computer program product for identification and improvement of machine learning (ML) under-performance The method comprises slicing data of ML model based on a functional model representing requirements of a system utilizing the ML model. The functional model comprises a set of attributes and respective domain of values. Each data slice is associated with a different valuation of one or more attributes of the functional model. Each data instance of the ML model is mapped to one or more data slices, based on valuation of the attributes. A performance measurement of the ML model over is computed for each data slice, based on an application of the ML model on each data instance that is mapped to the data slice. A Determination whether ML model adheres to a target performance requirement may be performed based on the performance measurements of the data slices.

Data slicing for machine learning performance testing and improvement

A method for automatically avoiding fault paths in software code of a System Under Test (SUT) includes generating a plurality of fingerprints by executing a plurality of regression tests. Each of the plurality of fingerprints uniquely identifies a specific code path in the software code of the SUT. A critical error is detected during execution of the software code of the SUT. A fault code path in the software code of the SUT associated with the critical error is identified by analyzing the plurality of generated fingerprints. At least one fingerprint associated with the fault code path in the software code of the SUT is identified. During subsequent execution of the software code of the SUT, the identified fault code path in the software code of the SUT is automatically prevented from being executed based on the identified at least one fingerprint.

Self healing software utilizing regression test fingerprints

Systems, methods, and computer-readable media are described for performing fault detection and localization using Combinatorial Test Design (CTD) techniques and generating a regression bucket of test cases that expose a detected fault in a System Under Test (SUT). The SUT may be a hardware system or a software system. Further, the fault detection and localization may be performed while adhering to architectural restrictions on the SUT.

Growing community of inventors

Haifa, Israel

Rachel Brill