Abstract: In an example, a query for a generative artificial intelligence (AI) tool may be received from a client device. A database including query autosuggestion profiles may be accessed to identify a set of query autosuggestion profiles matching the query. A set of query autosuggestions may be generated based upon the query and the set of query autosuggestion profiles. An autosuggestion interface indicative of the set of query autosuggestions may be provided on the client device. In response to receiving a selection of a first query autosuggestion of the set of query autosuggestions via the autosuggestion interface, the generative AI tool may be used to generate a first content item based upon the first query autosuggestion. The first content item may be provided for presentation on the client device.

Abstract: In an example, a prompt for a generative AI tool may be received from a client device. A first prompt modification profile matching the prompt may be identified. The prompt may be modified based upon the first prompt modification profile to generate an updated prompt. Using the generative AI tool, a first content item may be generated based upon the updated prompt. A first content modification profile matching at least a portion of the first content item may be identified. The first content item may be modified based upon the first content modification profile to generate an updated content item. The updated content item may be provided for presentation on the client device.

Abstract: In an example, a first content item is provided for display on a first client device. A first feedback signal is received. The first feedback signal is indicative of one or more first user reactions to display of the first content item on the first client device. The first content item is provided for display on a second client device. A second feedback signal is received. A first popularity score associated with the first content item is determined based upon the first feedback signal and the second feedback signal. A first popularity label is assigned to the first content item based upon the first popularity score. An enhanced content presentation interface including the first content item is generated based upon the first popularity label assigned to the first content item. The enhanced content presentation interface including the first content item is presented on a third client device.

Abstract: An error bound that indicates how well a hypothesis function approximates an unknown target function over a set of out-of-sample examples is computed from known error bounds for basis functions, as follows. An optimization problem is formed in which basis function error bounds imply constraints on feasible outputs of the target function over out-of-sample inputs. The optimization problem is solved to find an upper bound on the differences between the hypothesis function outputs and feasible target function outputs. This upper bound is a an error bound for the hypothesis function.

Abstract: Given a set of basis functions, a set of example inputs, and a set of uniform error bounds for the basis functions over the example inputs, a quadratic program is formed. The quadratic program is solved, producing a solution vector and a solution value. A hypothesis function is formed through fusion by using the solution vector to weight the outputs of the basis function. The hypothesis function is a function with minimum error bound among the functions formed by convex combination of basis function outputs. The solution value is an error bound for the hypothesis function. The error bound is logically implied by the uniform error bounds over the basis functions rather than uniform error bounds over the entire class of functions formed by convex combination of basis function outputs.

Abstract: A computer-based system computes a probabilistic bound on the error probability of a nearest neighbor classifier as follows. A subset of the examples in the classifier is used to form a reduced classifier. The error frequency of the reduced classifier on the remaining examples is computed as a baseline estimate of the error probability for the original classifier. Additionally, subsets of the examples outside the reduced classifier are combined with the reduced classifier and applied to the remaining examples in order to estimate the difference in error probability for the reduced classifier and error probability for the original classifier.

Abstract: An improvement to an automatic data extractor has the capability of discovering new values that are not recognized by the vocabulary of the automatic data extractor and adding them to the record being formed and to the vocabulary, thus accumulating new vocabulary through use. The extractor gleans new values by deducing them from the structure of the text data and learns them by adding them to its vocabulary. The data extractor determines the structure of the data in much the same way as prior art data extractors but then a discovery process is used to identify a series of field lists using preferably at least one field parser and a field grader. The results of the grader are returned to an attribute mapper that identifies the position in the field list for each of the attributes.