Abstract: A system and method for predicting a condition of a subject may include one or more autoencoder modules, trained to: receive at least one content data element pertaining to the subject from one or more data sources of a plurality of data sources; and generate a source-invariant representation of the at least one content data element in a latent space of the one or more autoencoders. One or more machine-learning (ML) based classification models may receive the source-invariant representation of the at least one content data element, and produce therefrom a prediction data element, which may represent a predicted condition of the subject.

Abstract: A user-annotated reference implementation identifies variable values generated by the reference implementation during its execution. A software implementation under analysis is executed. Variable values in the running memory of the program code of the software implementation under analysis, during its execution, are identified and copied. The variable values traced from the running memory of the program code are compared against the annotated variable values generated by the reference implementation, to determine a similarity between the program code under analysis, and the reference implementation. An output is generated that is indicative of whether the traced variables from the program code under analysis are the same as the annotated variable values generated by the reference implementation.

Abstract: A user-annotated reference implementation identifies variable values generated by the reference implementation during its execution. A software implementation under analysis is executed. Variable values in the running memory of the program code of the software implementation under analysis, during its execution, are identified and copied. The variable values traced from the running memory of the program code are compared against the annotated variable values generated by the reference implementation, to determine a similarity between the program code under analysis, and the reference implementation. An output is generated that is indicative of whether the traced variables from the program code under analysis are the same as the annotated variable values generated by the reference implementation.

Abstract: Techniques for using different data sources for a predictive model are described. According to various implementations, techniques described herein enable different data sets to be used to generate a predictive model, while minimizing the risk that individual data points of the data sets will be exposed by the predictive model. This aids in protecting individual privacy (e.g., protecting personally identifying information for individuals), while enabling robust predictive models to be generated using data sets from a variety of different sources.

Abstract: A training system is described herein for generating a prediction model that relies on a feature space with reduced dimensionality. The training system performs this task by producing partitions, each of which corresponds to a subset of aspect values (where each aspect value, in turn, may correspond to one or more attribute values). The training system then produces instances of statistical information associated with the partitions. Each instance of statistical information therefore corresponds to feature information that applies to a plurality of aspect values, rather than a single aspect value. The training system then trains the prediction model based on the feature information. Also described herein is a prediction module that uses the prediction model to make predictions in various online contexts.

Abstract: The techniques and/or systems described herein are directed to improvements in genomic prediction using homomorphic encryption. For example, a genomic model can be generated by a prediction service provider to predict a risk of a disease or a presence of genetic traits. Genomic data corresponding to a genetic profile of an individual can be batch encoded into a plurality of polynomials, homomorphically encrypted, and provided to a service provider for evaluation. The genomic model can be batch encoded as well, and the genetic prediction may be determined by evaluating a dot product of the genomic model data the genomic data. A genomic prediction result value can be provided to a computing device associated with a user for subsequent decrypting and decoding. Homomorphic encoding and encryption can be used such that the genomic data may be applied to the prediction model and a result can be obtained without revealing any information about the model, the genomic data, or any genomic prediction.

Abstract: The techniques and/or systems described herein are directed to improvements in homomorphic encryption to improve processing speed and storage requirements. For example, the techniques and/or systems can be used on a client device to encode data to be sent to a remote server, to be operated on while maintaining confidentiality of data. For example, data including a real number can be encoded as a polynomial, with the fractional part of the real number encoded as high-order coefficients in the polynomial. Further, real numbers can be approximated and encoded in a polynomial using a fractional base, and/or the encoding can include slot encoding. Thus, the optimized encodings disclosed herein provide an optimized homomorphic encryption scheme.

Abstract: Techniques for using different data sources for a predictive model are described. According to various implementations, techniques described herein enable different data sets to be used to generate a predictive model, while minimizing the risk that individual data points of the data sets will be exposed by the predictive model. This aids in protecting individual privacy (e.g., protecting personally identifying information for individuals), while enabling robust predictive models to be generated using data sets from a variety of different sources.

Abstract: Techniques for using data sets for a predictive model are described. According to various implementations, techniques described herein enable different data sets to be used to generate a predictive model, while minimizing the risk that individual data points of the data sets will be exposed by the predictive model. This aids in protecting individual privacy (e.g.

Abstract: The techniques and/or systems described herein are directed to improvements in homomorphic encryption to improve processing speed and storage requirements. For example, the techniques and/or systems can be used on a client device to encode data to be sent to a remote server, to be operated on while maintaining confidentiality of data. The encoding scheme can be optimized by automatically selecting one or more parameters using an error growth simulator based on an actual program that operates on the encoded data. For example, the simulator can be used iteratively to determine an optimized parameter set which allows for improved homomorphic operations while maintaining security and confidentiality of a user's data.

Abstract: A modern, personalized, adaptive learning experience may be enabled for distinct groups of students. Content entered in a notebook application or similar platform may be analyzed. Content from a learning object repository may then be selected to be suggested based on comparison with the entered content. A style may also be determined based on one or more of a common attribute of a group of teachers, a common attribute of a group of students, or a rule of an organization. The selected content to be suggested may be automatically customized to conform to the style and a lesson plan, and the customized content may be provided to a client application or another service to be displayed in conformance with the lesson plan to students supporting teachers by freeing teachers' time through optimization of the learning process, creation of easy and simple to use experiences, and actionable analytics and proactive alerts.

Abstract: The description relates to 3D gesture recognition. One example gesture recognition system can include a gesture detection assembly. The gesture detection assembly can include a sensor cell array and a controller that can send signals at different frequencies to individual sensor cells of the sensor cell array. The example gesture recognition system can also include a gesture recognition component that can determine parameters of an object proximate the sensor cell array from responses of the individual sensor cells to the signals at the different frequencies, and can identify a gesture performed by the object using the parameters.

Abstract: Embodiments described herein are directed to methods and systems for performing neural network computations on encrypted data. Encrypted data is received from a user. The encrypted data is encrypted with an encryption scheme that allows for computations on the ciphertext to generate encrypted results data. Neural network computations are performed on the encrypted data, using approximations of neural network functions to generate encrypted neural network results data from encrypted data. The approximations of neural network functions can approximate activation functions, where the activation functions are approximated using polynomial expressions. The encrypted neural network results data are communicated to the user associated with the encrypted data such that the user decrypts the encrypted data based on the encryption scheme. The functionality of the neural network system can be provided using a cloud computing platform that supports restricted access to particular neural networks.

Abstract: The techniques and/or systems described herein are directed to improvements in homomorphic operations within a homomorphic encryption scheme. The homomorphic operations may be performed on encrypted data received from a client device without decrypting the data at a remote computing device, thereby maintaining the confidentiality of the data. In addition to the operations of addition, subtraction, and multiplication, the homomorphic operations may include an approximate division, a sign testing, a comparison testing, and an equality testing. By combining these operations, a user may perform optimized operations with improved processor and memory requirements.

Abstract: Techniques and architectures may be used to provide an environment where a data owner storing private encrypted data in a cloud and a data evaluator may engage in a secure function evaluation on at least a portion of the data. Neither of these involved parties is able to learn anything beyond what the parties already know and what is revealed by the function, even if the parties are actively malicious. Such an environment may be useful for business transactions, research collaborations, or mutually beneficial computations on aggregated private data.

Abstract: The techniques and/or systems described herein are directed to improvements in genomic prediction using homomorphic encryption. For example, a genomic model can be generated by a prediction service provider to predict a risk of a disease or a presence of genetic traits. Genomic data corresponding to a genetic profile of an individual can be batch encoded into a plurality of polynomials, homomorphically encrypted, and provided to a service provider for evaluation. The genomic model can be batch encoded as well, and the genetic prediction may be determined by evaluating a dot product of the genomic model data the genomic data. A genomic prediction result value can be provided to a computing device associated with a user for subsequent decrypting and decoding. Homomorphic encoding and encryption can be used such that the genomic data may be applied to the prediction model and a result can be obtained without revealing any information about the model, the genomic data, or any genomic prediction.

Abstract: Systems, methods, apparatuses, and computer program products are described for implementing a digital personal assistant. The digital personal assistant is capable of determining that a user has asked a question or made a statement that is intended to engage with a persona of the digital personal assistant. In response to determining that the user has asked such a question or made such a statement, the digital personal assistant provides a response thereto by displaying or playing back a multimedia object associated with a popular culture reference within or by a user interface of the digital personal assistant. Additionally or alternatively, in response to determining that the user has asked such a question or made such a statement, the digital personal assistant provides the response thereto by generating or playing back speech that comprises an impersonation of a voice of a person associated with the popular culture reference.

Abstract: A system is provided that predicts eating events for a user. The system includes a set of sensors each of which is configured to continuously measure a different physiological variable associated with the user and output a time-stamped data stream that includes the current value of this variable. A set of features is periodically extracted from the data stream output from each of the sensors, where these features have been determined to be specifically indicative of an about-to-eat moment. This set of features is then input into an about-to-eat moment classifier that has been trained to predict when the user is in an about-to-eat moment based on this set of features. Whenever an output of the classifier indicates that the user is currently in an about-to-eat moment, the user is notified with a just-in-time eating intervention.

Abstract: The techniques and/or systems described herein are directed to improvements in homomorphic operations within a homomorphic encryption scheme. The homomorphic operations may be performed on encrypted data received from a client device without decrypting the data at a remote computing device, thereby maintaining the confidentiality of the data. In addition to the operations of addition, subtraction, and multiplication, the homomorphic operations may include an approximate division, a sign testing, a comparison testing, and an equality testing. By combining these operations, a user may perform optimized operations with improved processor and memory requirements.

Abstract: The techniques and/or systems described herein are directed to improvements in homomorphic encryption to improve processing speed and storage requirements. For example, the techniques and/or systems can be used on a client device to encode data to be sent to a remote server, to be operated on while maintaining confidentiality of data. For example, data including a real number can be encoded as a polynomial, with the fractional part of the real number encoded as high-order coefficients in the polynomial. Further, real numbers can be approximated and encoded in a polynomial using a fractional base, and/or the encoding can include slot encoding. Thus, the optimized encodings disclosed herein provide an optimized homomorphic encryption scheme.