Abstract: An inferential people recommender method and system infers the preferences of users from usage behaviors and generates recommendations of people based upon the matching of the inferred preferences. Natural language-based explanations that provide the reasoning that is applied in making the recommendations are also provided. The inferences of preferences may be determined by inference weightings that are in accordance with behavioral-based priority rules. The inferences may be further based on factors such as proximity, and duration of proximity, of people to physical objects, including other people.

Abstract: Adaptively interacting neural network-based systems interact with each other and then automatically analyze the results of the interactions by application of computer implemented neural networks. Structural subsets of the systems are then automatically modified based upon the results of the analysis. Information that results of from the interactions may comprise text-based and/or pictorial-based information. Modifications of the structural subsets may include iteratively modifying relationships among the elements of the systems and/or modifying relationship indicators that are associated with relationships among elements of the systems.

Abstract: Adaptive recommendations that reference users of computer-implemented systems are generated based upon subscription-based relationships among the users of the computer-implemented systems and the recommendations are further based upon inferences of user preferences from user behavioral information. Behavioral-based priority rules may be applied in generating the inferences. Natural language-based explanations that explain the reasoning for the recommendations may be delivered to recommendation recipients. The explanations may further reference subscription relationships among users.

Abstract: A method and system for self-propelled vehicles infers mobility aspects, such as speed and direction, of physical objects represented in digital maps. The physical objects may be further interpreted from pictorial-based information through the application of computer-implemented neural networks. Information is delivered to adaptive systems embodied within self-propelled vehicles that is based upon the mobility inferences and the interpretations from the pictorial information. Explanations for the delivered information comprising the system's reasoning and/or references to mobility inferences may also be delivered.

Abstract: Methods and systems for video-based adaptive recommendations deliver recommendations to users that are based upon inferences from user behaviors, and further, from interpretations of pictorial-based information associated with video content through the application of computer-implemented neural networks. The recommendations may refer to information that is interpreted from the pictorial-based information such as representations of physical objects. Natural language-based explanations for the delivered recommendations that explain the reasoning that is applied in making the recommendations may be provided to recommendation recipients.

Abstract: A neural network-based inferential advertising system and method delivers interactive advertisements to advertisement recipients in accordance with user-selected restrictions that inform the behavioral information upon which advertising preference inferences are made, as well as advertising preference inferences that are made based upon interpretations made from content by a computer-implemented neural network. The behavioral information upon which advertising inferences are made may include bodily movements of advertisement recipients that are performed without physical interaction with a device. Interactions by advertising recipients with delivered advertisements may include oral and gesture-based interactions.

Abstract: A method and system of inferential-based communications applies two sets of values, whereby the first set of values are determined from inferences of the relevancy of textual elements with respect to text-based content and the second set of values are determined from behavioral-based inferences with respect to topics, so as to select appropriate words to be included in communications that are generated for delivery to a user. The inferences that are with respect to text-based content may be determined by applying analytic methods such as Bayesian or statistical learning-based methods. The values that are determined from behavioral-based inferences with respect to topics may correspond to inferences of interest and/or expertise. Words in the communications may be selected and/or arranged in accordance with syntactical rules and may reference elements of the text-based content and/or behavioral inferences.

Abstract: A self-assembling learning system and apparatus determines self-assembling actions that are expected to reduce uncertainties that are embodied as probabilities and then updates the probabilities in accordance with information that results from the performing of the self-assembling actions. The updated probabilities inform the determination of subsequent self-assembling actions. Neural networks, simulations of multiple potential self-assembling actions, and expected values of information may be applied in determining the self-assembling actions that are to be performed. Sensors may be applied to receive information that inform the updating of probabilities, and the self-assembling apparatus may be a robotic device. Self-assembling actions may comprise modifications to relationships between elements of a computer-implemented system.

Abstract: A serendipity generating method, system, and device generates recommendations by identifying contrasting corresponding topic affinity values between users who more generally have a relatively high degree of similarity between corresponding topic affinity values. The topic affinity values may represent user interests with respect to topics and the topic affinity values may be inferred from usage behaviors, including geographic location information. Recommendations may be further in accordance with an assessment of the amount or quality of the usage behaviors from which the topic affinity values are derived and/or in accordance with the application of a probabilistic process. The recommendations may comprise computer-implemented objects that have relatively high affinities to topics associated with the contrasting corresponding topic affinity values.

Abstract: A method and system of expertise discovery in social networks accesses behavioral information associated with users' use of a computer-implemented social network, whereby the computer-implemented social network enables its users to have subscribing relationships with other users. Expertise levels of users of the social network with respect to one or more topics are automatically inferred from the behavioral information. The behavioral information may comprise interactions by other users with respect to content published by a user. The expertise levels of users may be inferred in accordance with the expertise levels of other users who are subscribed to them. Recommendations of users based on their expertise levels may be delivered, as well as explanations for the recommendations. Expertise levels of multiple users and/or expertise levels of a user over time may be delivered for display.

Abstract: An adaptive probabilistic computer-controlled method and system determines computer-controlled actions that are expected to reduce uncertainties that are embodied as probabilities and then updates the probabilities in accordance with the results of the computer-controlled actions. The updated probabilities inform the determination of subsequent computer-controlled actions. Expected values of information may also be applied in determining the subsequent computer-controlled actions. The computer-controlled actions may comprise analysis of content and generating recommendations that are delivered to users, and inferences from the analysis of content and usage behaviors may inform the updating of the probabilities. Statistical learning functions and/or neural networks may be applied in determining the computer-controlled actions.

Abstract: A stream of attention method, system, and apparatus determines a first focus of attention by applying a probabilistic analysis to a first set of syntactical elements. The syntactical elements may be derived from external communications or from communications generated internally by a computer-implemented system. Alternatively, the syntactical elements may be determined based on their association with images accessed from an external or internal source. Actions are performed by the computer-implemented system that are expected to reduce uncertainty with respect to the focus of attention. Such actions may include posing syntactical-based interrogatives directed to external entities or internally, searching a corpus of content, and/or moving to a new location and receiving input at the new location.

Abstract: A method and system of expertise discovery in social networks accesses behavioral information associated with users' use of a computer-implemented social network, whereby the computer-implemented social network enables its users to have subscribing relationships with other users. Expertise levels of users of the social network with respect to one or more topics are automatically inferred from the behavioral information. The behavioral information may comprise interactions by other users with respect to content published by a user. The expertise levels of users may be inferred in accordance with the expertise levels of other users who are subscribed to them. Recommendations of users based on their expertise levels may be delivered, as well as explanations for the recommendations. Expertise levels of multiple users and/or expertise levels of a user over time may be delivered for display.

Abstract: A serendipity generating method, system, and device generates recommendations by identifying contrasting corresponding topic affinity values between users who more generally have a relatively high degree of similarity between corresponding topic affinity values. The topic affinity values may represent user interests with respect to topics and the topic affinity values may be inferred from usage behaviors, including geographic location information. Recommendations may be further in accordance with an assessment of the amount or quality of the usage behaviors from which the topic affinity values are derived and/or in accordance with the application of a probabilistic process. The recommendations may comprise computer-implemented objects that have relatively high affinities to topics associated with the contrasting corresponding topic affinity values.

Abstract: An adaptive probabilistic computer-controlled method and system determines computer-controlled actions that are expected to reduce uncertainties that are embodied as probabilities and then updates the probabilities in accordance with the results of the computer-controlled actions. The updated probabilities inform the determination of subsequent computer-controlled actions. Expected values of information may also be applied in determining the subsequent computer-controlled actions. The computer-controlled actions may comprise analysis of content and generating recommendations that are delivered to users, and inferences from the analysis of content and usage behaviors may inform the updating of the probabilities. Statistical learning functions and/or neural networks may be applied in determining the computer-controlled actions.

Abstract: A self-referential semantic-based method, system, and device links semantic chains comprising subject, predicate, and objects of the predicate and optionally, an associated probability, with behavioral-based chains comprising a computer-implemented system, predicate, and an object of the predicate, and generates self-referential communications based on the linked chains. The self-referential communications may include metaphorical and/or imaginative constructs, and may convey a sense of confidence or what has been learned over time in accordance with weightings associated with the semantic and/or behavioral chains. The self-referential semantic-based device may take the form of a self-propelled apparatus, including an apparatus in humanoid form.

Abstract: A content-based expertise level inferencing system and method analyzes content such as text-based content that is associated with a user and infers an expertise level of the user that is associated with a topic. Language-based analytic techniques may be applied in inferring the expertise level, including the application of domain-specific vocabulary and frequency analyzes. The expertise level may be further inferred based on usage behaviors of the user and/or other users. Calibration information may be applied in generating the inference of the expertise level. Recommendations may be generated based on the inferred expertise level, and explanations for the recommendation and/or the inference may be generated for delivery to a recommendation recipient.

Abstract: A directed expertise level-based discovery system, method, and device infers an expertise level associated with a system user from a plurality of usage behaviors and delivers one or more computer-implemented objects to the user that are selected in accordance with the inferred expertise level and a directionally distinct relationship between computer-implemented objects. The directed expertise level-based discovery system, method, and device may infer the expertise level from textual information and/or in accordance with calibration information such as test results. Geographic location awareness associated with a portable device may inform the selection of the computer-implemented objects to be delivered to the user. An explanation may be delivered to the user that references information that is used to inform the selection of the computer-implemented objects to be delivered to the user.

Abstract: A personalized activity stream system, method, and device delivers a recommendation that is contextualized basis a selected item in an activity stream and that is personalized for a recommendation recipient consistent with an inference of the recommendation recipient's interests. Contextualization and personalization may be based on an automatic analysis of usage behaviors and/or content. The recommendation may be informed by an inference of an expertise level, and an explanation for the recommendation may be delivered to the recommendation recipient. The recommendation may be in accordance with an automatically determined geographic location associated with a location-aware portable device, as well as environmental conditions proximal to the portable device.

Abstract: A computer-implemented adaptive experimentation method and system is described that automatically selects and executes information gathering actions. The adaptive experimentation method and system integrates value of information considerations, experimental design, and inferences from experimental results. The experimental results may include behaviors of users of a computer-based system. The process enables an automatic, adaptive process for attaining additional information and applying the attained information in making subsequent experiment decisions.