Abstract: 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.

Abstract: One or more computer processors compute a maximum likelihood path matrix comprising a respective shortest path between each state in a set of states associated with a model trained with a deep reinforcement learning policy. The one or more computer processors generate explanations for the deep reinforcement learning policy based one or more identified meta-states for each state in the set of states and corresponding selected strategic states utilizing the computed maximum likelihood path matrix.

Abstract: 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 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.

Abstract: A method, computer program, and computer system are provided for providing artificial intelligence explanations. An explanation request corresponding to an output or a behavior of an artificial intelligence system is received from a user. A context or user profile associated with the user is identified. A plurality of explanation methods corresponding to the artificial intelligence system is accessed. Each explanation method provides an independent explanation for the output or the behavior of the artificial intelligence system and is rated based on a set of explanation evaluation criteria corresponding to the context or user profile. An explanation method having a highest rating is selected from among the plurality of explanation methods, and an explanation of the output or the behavior of the artificial intelligence system corresponding to the selected explanation method to the user.

Abstract: 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.

Abstract: 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 ?.

Abstract: An approach to generate a path for minimally sufficient explanations for improving model understanding. Data is received from a user. The data is iteratively processed to generate minimally sufficient explanations based on the input data and the input of a subsequent explanation determination is constrained to the output of a prior explanation determination.

Abstract: 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.

Abstract: 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.

Abstract: 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 ?.

Abstract: 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.

Abstract: A method, system, and computer program product including generating random test inputs as a number of queries using a token and analyzing a correlation between a system failure and a token present in respective inputs to localize the system failure.

Abstract: 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.

Abstract: 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.

Abstract: A method, system, and computer program product, including highlighting a minimally sufficient component in an input to justify a classification, identifying contrastive characteristics or features that are minimally and critically absent, maintaining the classification and distinguishing it from a second input that is closest to the classification but is identified as a second classification.

Abstract: 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.

Abstract: In a method for analyzing social media messages, the method includes one or more processors analyzing social media messages utilizing a set of topics and keywords associated with a brand. The method further includes one or more processors identifying social media messages that include information relating to the brand utilizing the analysis of social media messages utilizing the set of topics and keywords. The method further includes one or more processors determining relevancy scores for the identified social media messages that provide an indication of the percentage likelihood that a social media message is related to the brand. The method further includes one or more processors determining one or more recommendations of social media users associated with social media messages based on the determined relevancy scores.