Texas Instruments Corporation

William Marsh Rice University

Andrew E Waters

Richard G Baraniuk

Charles Kasimer Sestok, Iv

Christoph Emanuel Studer

Shiting Lan

Divyanshu Vats

Andrew S Lan

Mechanisms for automatically grading a large number of solutions provided by learners in response to an open response mathematical question. Each solution is mapped to a corresponding feature vector based on the mathematical expressions occurring in the solution. The feature vectors are clustered using a conventional clustering method, or alternatively, using a presently-disclosed Bayesian nonparametric clustering method. A representative solution is selected from each solution cluster. An instructor supplies a grade for each of the representative solutions. Grades for the remaining solutions are automatically generated based on their cluster membership and the instructor supplied grades. The Bayesian method may also automatically identify the location of an error in a given solution. The error location may be supplied to the learner as feedback. The error location may also be used to extract information from correct solutions. The extracted information may be supplied to a learner as a solution hint.

Mathematical language processing: automatic grading and feedback for open response mathematical questions

A mechanism for discerning user preferences for categories of provided content. A computer receives response data including a set of preference values that have been assigned to content items by content users. Output data is computed based on the response data using a latent factor model. The output data includes at least: an association matrix that defines K concepts associated with the content items, wherein K is smaller than the number of the content items, wherein, for each of the K concepts, the association matrix defines the concept by specifying strengths of association between the concept and the content items; and a concept-preference matrix including, for each content user and each of the K concepts, an extent to which the content user prefers the concept. The computer may display a visual representation of the association strengths in the association matrix and/or the extents in the concept-preference matrix.

Sparse factor analysis for analysis of user content preferences

Compressive sensing is an emerging field that attempts to prevent the losses associated with data compression and improve efficiency overall, and compressive sensing looks to perform the compression before or during capture, before energy is wasted. Here, a reconstruction algorithm is proposed for a compressive sensing successive approximation register (SAR) analog-to-digital converter (ADC). Accordingly, an analog signal is converted to a first digital signal at a sampling frequency that is less than a Nyquist frequency for the analog signal, and a second digital signal is constructed from the first digital signal with a box constrained linear optimization process such that the second digital signal is approximately equal to an analog-to-digital conversion of the analog signal at the Nyquist frequency for the analog signal.

Compressive sense based reconstruction algorithm for non-uniform sampling based data converter

A calibration method to compensate for a sparsifying basis mismatch is provided. An analog signal is converted to a first digital signal at a sampling frequency that is less than a Nyquist frequency for the analog signal to generate a first digital signal. Each of a plurality of spectral terms is iteratively isolated from the first digital signal, and the offset for each of the plurality of spectral terms is iteratively determined. A dictionary is then constructed using the offset for each of the plurality of spectral terms, where the dictionary compensates for mismatch from a sparsifying basis.

Growing community of inventors

Sugar Land, TX, United States of America

Andrew E Waters