Method and system for providing user-specific explanations for output generated by artificial neural network model

A system for providing user-specific explanations for an output generated by an ANN model, the system comprising:

• a vocabulary and explanation generating device comprising at least one processor and a computer-readable medium storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
• receiving a training dataset;
• identifying one or more relevant features from the training dataset, wherein the one or more relevant features are identified from a plurality of features associated with the training dataset, and wherein each of the plurality of features correspond to a neuron activated in the ANN model for generating an output for the training dataset, wherein identifying further selecting the one or more relevant features from the plurality of features associated with the training dataset based on a predetermined threshold level of activation of the neuron corresponding to the each of the plurality of features;
• distributing the one or more relevant features into a plurality of groups, wherein the plurality of groups correspond to a plurality of levels of domain knowledge of users;
• and
• generating a plurality of vocabularies of explanations for an output generated by the ANN model for the training dataset corresponding to the plurality of groups, using the one or more relevant features.

A non-transitory computer-readable medium storing computer-executable instructions for providing user-specific explanations for an output generated by an Artificial Neural Network (ANN) model, the computer-executable instructions, when executed by at least one processor, cause the at least one processor to perform operations comprising:

• receiving a training dataset;
• identifying one or more relevant features from the training dataset, wherein the one or more relevant features are identified from a plurality of features associated with the training dataset, and wherein each of the plurality of features correspond to a neuron activated in the ANN model for generating an output for the training dataset, wherein identifying further comprising selecting the one or more relevant features from the plurality of features associated with the training dataset based on a predetermined threshold level of activation of the neuron corresponding to the each of the plurality of features;
• distributing the one or more relevant features into a plurality of groups, wherein the plurality of groups corresponds to a plurality of levels of domain knowledge of users;
• and
• generating a plurality of vocabularies of explanations for an output generated by an ANN model for the training dataset corresponding to the plurality of groups, using the one or more relevant features.