Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for oversampling training data for training a machine learning model. In some implementations, techniques described enable debiasing of trained models through oversampling of training data. In general, training data can be partitioned into multiple levels corresponding to specific elements of data, e.g., type of tumor, type of individual, time of day, among others. A given level can be associated with higher bias than other levels. For example, input data of a particular type of individual, such as an individual of a certain age range or with certain genetic traits, can cause corresponding machine learning model predictions or results that are more biased compared to other data. Higher bias can include an increased number of false positives or false negatives for Boolean model predictions or predictions.

Abstract: Systems and methods for providing an explainability framework for use with AI systems are described. In one example, such an AI explainability system for intent classification uses a surrogate Bert-Siamese model approach. For example, a prediction from an intent classification model is paired with a top matching sentence and used as input to train a Bert-Siamese model for sentence similarity. Using the sentence similarity, the token/word level embedding can be extracted from attention weights of the sentences and correlations between query tokens/words, and the best matching sentences may be used for explanations.

Abstract: Systems and methods for computing feature contribution and providing hum-interpretable reason codes for a Support Vector Machine (SVM) model are disclosed, A system computes, for each data point from amongst plurality of data points indicative of plurality of features, a feature contribution of each one of the plurality of features for a SVM model used for at least one of classification decision and a regression analysis. Further, the system provides human interpretable reason code for the interpretation corresponding to at least one of classification decision and the regression analysis from the SVM model. The system outputs to the user, a feature contribution output, and the human interpretable reason codes output. The feature contribution output and the human interpretable reason codes output are indicative of an acceptable decision to be taken by the user based on the classification decision and the regression analysis received from the SVM model.

Abstract: Examples of a prediction explanation system are be provided. The system may obtain a first data record comprising multiple case instances and a first data record neural network providing multiple predictions, each prediction being associated with a case instance. Each case instance may be analyzed to determine a corresponding hidden neuron contribution score, which may be used for clustering the cases instances into multiple instance clusters. For each instance cluster, a decision tree model may be generated, where a decision tree model comprises an explanation for a prediction associated with the case instance in the instance cluster. For a second data record obtained by the system, a second data index comprising a cluster mapping score assigned to each decision tree model may be determined. Based on the decision trees model with a highest cluster mapping score, a second data prediction output providing an explanation for a prediction may be generated.