Abstract: Representative embodiments disclose mechanisms for dynamically adjusting the user interface and/or behavior of an application to accommodate continuous and unobtrusive learning. As a user gains proficiency in an application, the learning cues and other changes to the application can be reduced. As a user loses proficiency, the learning cues and other changes can be increased. User emotional state and openness to learning can also be used to increase and/or decrease learning cues and changes in real time. The system creates multiple learning models that account for user characteristics such as learning style, type of user, and so forth and uses collected data to find the best match. The selected learning model can be further customized to a single user. The model can also be tuned based on user interaction and other data. Collected data can also be used to adjust the base learning models.

Abstract: Methods, systems, and computer programs are presented for notifying users of identified bias when the users make decisions. One method includes an operation for tracking, by a bias machine-learning program (MLP), the activities of a user. A set of features is defined for detecting bias, where the features include user profile information, user environment information, history of activities and decisions of the user, community information, and a knowledge base that includes facts. Additionally, the bias MLP detects a decision of the user based on the tracked activities, and analyzes the decision for bias when making the decision. The analysis is based on the decision, facts relevant to making the decision, and the features utilized by the bias MLP. When a bias is detected, a notification is presented to the user of the detection of the bias, with one or more reasons for the detected bias.

Abstract: Representative embodiments disclose mechanisms for dynamically adjusting the user interface and/or behavior of an application to accommodate continuous and unobtrusive learning. As a user gains proficiency in an application, the learning cues and other changes to the application can be reduced. As a user loses proficiency, the learning cues and other changes can be increased. User emotional state and openness to learning can also be used to increase and/or decrease learning cues and changes in real time. The system creates multiple learning models that account for user characteristics such as learning style, type of user, and so forth and uses collected data to find the best match. The selected learning model can be further customized to a single user. The model can also be tuned based on user interaction and other data. Collected data can also be used to adjust the base learning models.

Abstract: A user experience system discloses determining, using graphical positioning system (GPS) parameters, a geo-physical location of a vehicle, determining a traffic pattern encountered by the vehicle based in the geo-physical location of the vehicle, determining a value of user distraction level for a user in the vehicle, and changing presentation of user experience to the user based on the value of the user distraction level. In an alternative implementation, the vehicle is a semi-autonomous vehicle and determining the user distraction level for the user further comprises determining an amount of active driving of the semi-autonomous vehicle required of the user.