Abstract: Techniques can construct a learner's educational context (e.g., course enrollments, subject-matter interests, and/or activity involvements) and tailor query processing using the educational context. For a given query, each concept in a set of concepts can be assigned a weight. The weight can depend on a query term in the query. For example, for a query including “North America”, a “geography” concept and a “history” concept can be determined to be related to the query, and weights can be influenced accordingly. Weights can also depend on a user's educational context (e.g., such that the “geography” weight is higher when a learner is enrolled in a geography course). A query time can also be analyzed in view of schedule data (e.g., indicating when particular topics are to be studied in a course). Weights can further depend on which concepts are recently, currently or will soon be of interest based on the schedule.

Abstract: Dynamically updating neural network systems may be implemented to generate, train, evaluate and update artificial neural network data structures used by content distribution networks. Such systems and methods described herein may include generating and training neural networks, using neural networks to perform predictive analysis and other decision-making processes within content distribution networks, evaluating the performance of neural networks, and generating and training pluralities of replacement candidate neural networks within cloud computing architectures and/or other computing environments.

Abstract: Techniques can construct a learner's educational context (e.g., course enrollments, subject-matter interests, and/or activity involvements) and tailor query processing using the educational context. For a given query, each concept in a set of concepts can be assigned a weight. The weight can depend on a query term in the query. For example, for a query including “North America”, a “geography” concept and a “history” concept can be determined to be related to the query, and weights can be influenced accordingly. Weights can also depend on a user's educational context (e.g., such that the “geography” weight is higher when a learner is enrolled in a geography course). A query time can also be analyzed in view of schedule data (e.g., indicating when particular topics are to be studied in a course). Weights can further depend on which concepts are recently, currently or will soon be of interest based on the schedule.

Abstract: Techniques can construct a learner's educational context (e.g., course enrollments, subject-matter interests, and/or activity involvements) and tailor query processing using the educational context. For a given query, each concept in a set of concepts can be assigned a weight. The weight can depend on a query term in the query. For example, for a query including “North America”, a “geography” concept and a “history” concept can be determined to be related to the query, and weights can be influenced accordingly. Weights can also depend on a user's educational context (e.g., such that the “geography” weight is higher when a learner is enrolled in a geography course). A query time can also be analyzed in view of schedule data (e.g., indicating when particular topics are to be studied in a course). Weights can further depend on which concepts are recently, currently or will soon be of interest based on the schedule.