International Business Machines Corporation

Ronny Luss

Amit Dhurandhar

Karthikeyan Shanmugam

Pin-Yu Chen

Prasanna Sattigeri

Omer Tripp

Peder Andreas Olsen

Amar Prakash Azad

Saneem Ahmed Chemmengath

Dmitry M Malioutov

A method, computer program product and system are provided to generate perturbed text is provided. A processor receives a string of text from a user. A processor determines one or more classifications for at least one word in the string of text by a classification model. A processor determines a plurality of perturbations of the at least one word based on the one or more classifications, where the plurality of perturbations do not share the same one or more classifications as the at least one word in the string of text. A processor selects a perturbation of the string of text based on (i) an edit distance between the string of text and the plurality of perturbations, and (ii) a fluency metric for each of the plurality of perturbations. A processor provides the perturbation of the string of text to the user.

System and method for generating contrastive explanations for text guided by attributes

A method, system, and computer program product, including generating, using a linear probe, confidence scores through flattened intermediate representations and theoretically-justified weighting of samples during a training of the simple model using the confidence scores of the intermediate representations.

Simple models using confidence profiles

In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.

Contrastive explanations for images with monotonic attribute functions

A computer-implemented method, system, and non-transitory computer-readable storage medium for enhancing performance of a first model. The first model is trained with a training data set. A second model receives the training data set associated with the first model. The second model provides the first model with a hardness value associated with prediction of each data point of the training data set. The first model determines a confidence value regarding predicting each data point based on the training data set, and determines a ratio of the hardness value of a prediction of each data point by the second model with respect to the confidence value of the first model. The first model is retrained with a re-weighted training data set when the determined ratio is lower than a value of &#x3b2;.

Leveraging simple model predictions for enhancing computational performance

A Software optimization method, system, and computer program product, include defining a vocabulary of tokens to yield admissible inputs of a system, generating random test inputs based on combining inputs and input tuples, followed by application of these inputs into the system, and analyzing the correlations between system failures and the tokens present in respective inputs to localize failures to particular inputs and input tuples.

Growing community of inventors

New York, NY, United States of America

Ronny Luss