Abstract: In an embodiment, a GAN model is trained based on an image dataset. A set of images of a first class is generated by the GAN model. Further, a first saliency map of a first generated image is determined by a neural network model. A second saliency map of a second image, belonging to the first class, from image dataset is determined by the neural network model. A first interpretability coefficient is determined, based on the first and second saliency maps. A first typicality score between the first generated image and a first set of images, belonging to the first class, from the image dataset, is determined. A second typicality score between a pair of generated images is determined. A second interpretability coefficient is determined basis the first and second typicality scores. An interpretability score associated with the GAN model is determined based on the first and second interpretability coefficients.

Abstract: In an embodiment, a textual description of a situation of a first user is received. A first set of vector embeddings is determined based on the textual description. A set of ethical texts is received based on an input from a second user. A second set of vector embeddings is determined based on the set of ethical texts. A set of antonym words and a set of synonym words are determined with respect to the first set of vector embeddings, based on the second set of vector embeddings. A set of sentences is determined based on the set of antonym words and the set of synonym words. A first sentence is selected from the set of sentences based on parts-of-speech in each sentence. By using a GAN model, an image is generated based on the first sentence. The image is rendered on a display device associated with the second user.

Abstract: In an embodiment, multiple datasets related to multiple application domains are received. Further, feature dependency information associated with a first dataset is determined, based on a first user input. Also, feature difference information associated with the first dataset and a second dataset is determined, based on a second user input and a set of ethical requirements. A set of structural causal models (SCMs) associated with the first dataset are determined based on the feature dependency information and the feature difference information. A set of ethical coefficients associated with the set of ethical requirements are determined based on an application of a causal transportability model on the set of SCMs. A trust score associated with the first dataset is determined based on the set of ethical coefficients. The trust score is used to train a meta-learning model associated with the multiple application domains.

Abstract: In an embodiment, operations include extracting first information about a first set of features of a first candidate, from a document or profile information of the first candidate. Second information about a second set of features, corresponding to the first set of features, is extracted from one or more databases. The second set of features is associated with a population of candidates with at least one demographic parameter same as that of the first candidate. A third set of features is determined based on difference of corresponding features from the first set of features and the second set of features. A pre-trained neural network model is applied on the third set of features to determine a set of weights associated with the third set of features. An empathy score of the first candidate is determined based on the set of weights. The empathy score of the first candidate is rendered.

Abstract: In an embodiment, a textual description of a situation of a first user is received. A first set of vector embeddings is determined based on the textual description. A set of ethical texts is received based on an input from a second user. A second set of vector embeddings is determined based on the set of ethical texts. A set of antonym words and a set of synonym words are determined with respect to the first set of vector embeddings, based on the second set of vector embeddings. A set of sentences is determined based on the set of antonym words and the set of synonym words. A first sentence is selected from the set of sentences based on parts-of-speech in each sentence. By using a GAN model, an image is generated based on the first sentence. The image is rendered on a display device associated with the second user.

Abstract: According to an aspect of an embodiment, operations include controlling a user device to display a plurality of task-specific questions onto an electronic user interface (UI) of the user device. Each task-specific question corresponds to a check for presence of a bias in one of a sequence of development phases of a machine learning (ML) model. The operations further include receiving a first input comprising a plurality of user responses corresponding to the displayed plurality of task-specific questions and determining a set of biases associated with the ML model based on the received first input. The operations further include controlling the user device to display the determined set of biases and a set of plausible actions to mitigate an effect of the determined set of biases on the ML model.

Abstract: In an embodiment, a GAN model is trained based on an image dataset. A set of images of a first class is generated by the GAN model. Further, a first saliency map of a first generated image is determined by a neural network model. A second saliency map of a second image, belonging to the first class, from image dataset is determined by the neural network model. A first interpretability coefficient is determined, based on the first and second saliency maps. A first typicality score between the first generated image and a first set of images, belonging to the first class, from the image dataset, is determined. A second typicality score between a pair of generated images is determined. A second interpretability coefficient is determined basis the first and second typicality scores. An interpretability score associated with the GAN model is determined based on the first and second interpretability coefficients.

Abstract: A method may include obtaining a data set for analysis, and selecting at least one candidate of bias for predicting whether the data set includes a result that is biased based on the candidate. The method may also include generating a point cloud of the data set based on the candidate and the result. The method may additionally include computing, prior to performing classification on the data set using machine learning, persistence homology on the point cloud based on the candidate and the result. The method may also include plotting persistence barcodes based on the persistence homology, where the persistence barcodes may be indicative of a duration of complexes within the persistence homology, determining a length of a longest barcode in the persistence barcodes, and generating a quantification of the bias based on the longest barcode and a visualization of the bias based on the plot of the persistence barcodes.

Abstract: In an embodiment, operations include receiving first information associated with a first person and a first request of the first person to one or more institutions. A set of attributes of the first person is extracted and used to construct a causal model. The causal model represents causal relationships amongst attributes of the set of attributes. For the first person, a utility function associated with each of a plurality of AI models associated with the one or more institutions is determined. The utility function is determined based on the causal model, a first set of empathy criteria associated with the first person, and a second set of empathy criteria associated with each of the one or more institutions. For the utility function, optimin-point information is determined to reconcile a plurality of decisions taken by the plurality of AI models for the first request. The reconciled decision is rendered.

Abstract: In an embodiment, operations include extracting first information about a first set of features of a first candidate, from a document or profile information of the first candidate. Second information about a second set of features, corresponding to the first set of features, is extracted from one or more databases. The second set of features is associated with a population of candidates with at least one demographic parameter same as that of the first candidate. A third set of features is determined based on difference of corresponding features from the first set of features and the second set of features. A pre-trained neural network model is applied on the third set of features to determine a set of weights associated with the third set of features. An empathy score of the first candidate is determined based on the set of weights. The empathy score of the first candidate is rendered.

Abstract: A method may include obtaining a dialogue of a user and a pre-trained language model. The method may include obtaining a corpus of dialogues and a corpus of response materials. The method may include modifying the pre-trained language model. The method may include identifying a dialogue topic of the dialogue of the user and identifying a set of response topics. The method may include selecting a set of response materials from the corpus of response materials. The method may include determining a first plurality of probabilities and, for each response material of the set of response materials, a respective second plurality of probabilities. The method may include comparing the first plurality of words with each respective second plurality of words associated with each respective response material of the set of response materials. The method may include selecting a response material of the set of response materials based on the comparison.

Abstract: According to an aspect of an embodiment, operations include receiving user information comprising motion information associated with a group of users in a built environment and user preference information associated with a group of events hosted in the built environment. The operations further include receiving layout information associated with the built environment and schedule information associated with the group of events. The operations further include predicting event-specific action associated with each user based on the user information, and the layout and schedule information. The operations further include predicting a path for navigation towards an event location associated with one of the group of events based on the predicted event-specific action and historical movement information of the group of users. The operations further include selecting, from the predicted paths, one or paths for navigation and generating navigation suggestions based on the selected paths.

Abstract: A method may include obtaining a machine-learning model trained with respect to a subject. The machine-learning model may be based on a plurality of factors that correspond to the subject. The method may include obtaining human provided information regarding the subject. The expert information may indicate relationships between the plurality of factors with respect to how the plurality of factors affect each other. The method may include generating a structural causal model that represents the relationships between the plurality of factors based on the expert information. The method may include identifying, as a confounding factor and based on the structural causal model, a factor of the plurality of factors that causes a confounding bias in the machine-learning model. The method may include estimating the confounding bias based on the identified confounding factor.

Abstract: A method of estimating one or more conditional probabilities may be provided. A method may include determining one or more states based on user input, and determining a similarity measurement between at least one state pair of one or more state pairs. The method may further include determining a likelihood of probability for the at least one state pair of the one or more state pairs. Moreover, the method may include estimating a conditional probability for the at least one state pair of the one or more state pairs based on the determined likelihood of probability and the determined one or more states.

Abstract: According to an aspect of an embodiment, operations include receiving user information comprising motion information associated with a group of users in a built environment and user preference information associated with a group of events hosted in the built environment. The operations further include receiving layout information associated with the built environment and schedule information associated with the group of events. The operations further include predicting event-specific action associated with each user based on the user information, and the layout and schedule information. The operations further include predicting a path for navigation towards an event location associated with one of the group of events based on the predicted event-specific action and historical movement information of the group of users. The operations further include selecting, from the predicted paths, one or paths for navigation and generating navigation suggestions based on the selected paths.

Abstract: A method includes storing a plurality of textual conversations. Each textual conversation of the plurality of textual conversations corresponds to a plurality of textual messages shared between a plurality of agents and a plurality of customers. The method further includes retrieving a first set of textual conversations of a first time-period from the stored plurality of textual conversations. The first set of textual conversations correspond to a first agent of the plurality of agents. Further, the method includes determining a first set of features of each textual message in the retrieved first set of textual conversations of the first time-period. Furthermore, the method includes determining a first creativity score for the first agent based on the determined first set of features of the first set of textual conversations and generating behavioral communicative information, related to the first agent based on the determined first creativity score.

Abstract: According to an aspect of an embodiment, operations include controlling a user device to display a plurality of task-specific questions onto an electronic user interface (UI) of the user device. Each task-specific question corresponds to a check for presence of a bias in one of a sequence of development phases of a machine learning (ML) model. The operations further include receiving a first input comprising a plurality of user responses corresponding to the displayed plurality of task-specific questions and determining a set of biases associated with the ML model based on the received first input. The operations further include controlling the user device to display the determined set of biases and a set of plausible actions to mitigate an effect of the determined set of biases on the ML model.

Abstract: A method may include obtaining a dialogue of a user and a pre-trained language model. The method may include obtaining a corpus of dialogues and a corpus of response materials. The method may include modifying the pre-trained language model. The method may include identifying a dialogue topic of the dialogue of the user and identifying a set of response topics. The method may include selecting a set of response materials from the corpus of response materials. The method may include determining a first plurality of probabilities and, for each response material of the set of response materials, a respective second plurality of probabilities. The method may include comparing the first plurality of words with each respective second plurality of words associated with each respective response material of the set of response materials. The method may include selecting a response material of the set of response materials based on the comparison.

Abstract: A method of generating text using an adversarial network includes receiving a limited dataset. The limited dataset includes real data having actual parameters and actual sentences. The method includes receiving content data that includes a concept related to a portion of the real data or that causes an issue of the real data. The method includes generating relationships between the real data and the content data. The method includes embedding the content data with the real data in an encoder output that includes content vector embedding. The method includes generating an additional parameter set that includes additional parameters and one or more additional statements. The additional parameter set may be supplemental to the real data and configured to enhance an expressiveness of a model. The method includes generating explanatory statement based on the additional parameter set and the relationships.

Abstract: A method of generating text having related purposes using a generative adversarial network (GAN) includes receiving a limited dataset including real data with related cognitive value types (types). The method includes applying loss functions to portions of the real data. The portions of the real data are each identified as having one of the types. The loss functions ensure alignment of the portions with corresponding types. The method includes embedding the real data into an encoder output that includes an embedded vector for the cognitive value types. The method includes generating an additional parameter set supplemental to the real data and configured to enhance an expressiveness of a model. The method includes generating statements based on the additional parameter set and the encoder output. The statements include a style of one of the cognitive value types and are related to a common issue addressed by the GAN.