Abstract: Example apparatus disclosed include interface circuitry, machine readable instruction, and programmable circuitry to at least one of instantiate or execute the machine readable instructions to access source input data and target input data, identify a domain shift prediction based on at least one of a feature decorrelation of the source input data or a feature decorrelation of the target input data, the domain shift prediction a source domain prediction or a target domain prediction, initiate gradient propagation of a domain loss to determine data features for the domain shift prediction, and rank input data features for the domain shift prediction.

Abstract: System and techniques for tracking caloric expenditure using sensor driven fingerprints are described herein. A set of outputs may be obtained from a plurality of sensors. A fingerprint may be generated using the set of outputs. The fingerprint may correspond to an activity observed by the plurality of sensors. The generated fingerprint may be compared to a set of fingerprints stored in a database. Each fingerprint of the set of fingerprints may correspond to a respective caloric expenditure. A caloric expenditure may be calculated for the activity based on the comparison. An exercise profile of a user may be updated using the caloric expenditure.

Abstract: Data analysis and neural network training technology includes generates, based on a sparse neural network, a feature selection ranking representing a ranked list of features from input data, where the sparse neural network is a shallow neural network trained with the input data and then pruned, generates, based on the sparse neural network, a feature set dictionary representing interactions among features from the input data, and performs, based on the feature selection ranking and the feature set dictionary, one or more of generating an output analysis of insights from the input data and the sparse neural network, or training of a second neural network. The technology can also adjust the input data based on the feature set ranking to produce adjusted input data, where the sparse neural network is re-trained based on the adjusted input data and then pruned prior to generating the feature set dictionary.

Abstract: Examples disclosed herein provide real-time language learning within a smart space. An example system includes a sensor; object detection software to identify a first object and a second object in an environment based on an output of the sensor; assign a first weight to the first object and a second weight to the second object; perform a comparison of the first weight and the second weight; and select the first object to be associated with a second language output based on the comparison; context determination software to determine a second language context based on the output of the sensor; linguistic analysis software to associate the first object with a second language based on the second language context; and prompt generation software to cause the second language output for the first object in the second language to be presented.

Abstract: Systems, apparatuses and methods may provide for technology that selects a fractional derivative value, determines a derivative operation based on the fractional derivative value, applies the derivative operation to an activation function to obtain a deformable fractional filter, generates a mask based on the deformable fractional filter, and convolves the mask with input data.

Abstract: Systems and methods may provide for conducting an interest analysis of data associated with a user, wherein the interest analysis distinguishes between abstract interests and social interests. Additionally, one or more recommendations may be generated for the user based on the interest analysis and a current context of the user, wherein the one or more recommendations may be presented to the user. In one example, the abstract interests identify types of topics and types of objects, and the social interests identify types of social groups.

Abstract: Language education systems capable of integrating with a user's daily life and automatically producing educational prompts would be particularly advantageous. An example method includes determining a user's identity, detecting a language education subject, prompting the user with a language education message, receiving a user's response, and updating a user profile associated with the user based on the user's response. Methods may also include determining user state (including emotional, physical, social, etc.) and determining, based on the user state, whether to prompt the user with the language education prompt.

Abstract: An apparatus is provided for deep learning. The apparatus accesses a neural network including an input layer, hidden layers, and an output layer. The apparatus adds an activation function to one or more of the hidden layers of the hidden layers and output layer. The activation function includes a tunable parameter, the value of which can be adjusted during the training of the neural network. The apparatus trains the neural network by inputting training samples into the neural network and determining internal parameters of the neural network based on the training samples. Determining the internal parameters includes determining a value of the tunable parameter based on the training samples. The apparatus may determine two different values of the tunable parameter for two different layers. The activation function may include another tunable parameter. The apparatus can determine a value for the other tunable parameter during the training of the neural network.

Abstract: The present disclosure provides a machine learning model where each activation node within the model has an adaptive activation function defined in terms of an input and a hyperparameter of the model. Accordingly, each activation node can have a separate of distinct activation function, based on the adaptive activation function where the hyperparameter for each activation node is trained during overall training of the model. Furthermore, the present disclosure provides that a set of adaptive activation functions can be provided for each activation node such that a spike train of activations can be generated.

Abstract: In an embodiment, a system includes a wearable device having a sensor that detects whisper data from a user. The whisper data may include vibrational data, audio data, and/or biometric signals, and correspond to words whispered by the user at a first decibel level. The system also includes a processor communicatively coupled to the sensor that extracts features associated with the whisper data including frequencies and/or amplitudes associated with the whispered data, and generates speech data based on the whisper data and the features. The speech data corresponds to the words spoken at a second decibel level, where the second decibel level is greater than the first decibel level.

Abstract: Systems, devices, and techniques are provided for occupancy assessment of a vehicle. For one or more occupants of the vehicle, the occupancy assessment establishes position and/or identity for some or all of the occupant(s).

Abstract: Techniques to extract data from computer-readable purchase records of a user, cluster the items of interest based on descriptions of the items, and associate descriptive keywords to the clusters, where the keywords represent interests of the user. One or more processes and/or functions may be performed on extracted data, including cluster-specific processes and/or function, including user-based, user interest-based, and/or crowd-based processes and/or function, which may include shopping pattern extraction, item or types of items availability based on time, location and other contextual metric, pricing data of items and expected pricing changes over time and seasonal variations, identification of user preferences, and/or shopping recommendations.

Abstract: Technologies for light exposure analysis include a computer configured to collect light data of an environment and a remote computer communicatively coupled to the computer. The remote computer is configured to receive/retrieve health information for one or more users and analyze the health information to generate a health profile for each of the one or more users. Additionally, the remote computer is configured to determine whether any correlations exist between the health profiles and the light data. The remote computer is further configured to analyze the collected light data against one or more health profiles to determine a desired lighting condition for a user based at least in part on the correlations between the health profiles and the light data. Other embodiments are described and claimed.

Abstract: A method is provided. The method includes receiving inputs typed by a user of a keyboard and analyzing the inputs to identify typing errors made by the user. The method also includes customizing a layout of the keyboard to reduce the identified typing errors.

Abstract: Technologies for automated context-aware media curation include a computing device that captures context data associated with media objects. The context data may include location data, proximity data, behavior data of the user, and social activity data. The computing device generates inferred context data using one or more cognitive or machine learning algorithms. The inferred context data may include semantic time or location data, activity data, or sentiment data. The computing device updates a user context model and an expanded media object graph based on the context data and the inferred context data. The computing device selects one or more target media objects using the user context model and the expanded media object graph. The computing device may present context-aware media experiences to the user with the target media objects. Context-aware media experiences may include contextual semantic search and contextual media browsing. Other embodiments are described and claimed.

Abstract: In some embodiments, the disclosed subject matter involves identifying environmental factors and user context that affect sleep quality. Embodiments use information about the static sleep environment, as well as dynamic environmental factors, such as sound, light, movement, correlated with user context, such as physical and emotional state, as well, as recent behavior to classify sleep data. The correlated and classified sleep data may be used to provide change recommendations, where implementing the recommended change is believed to improve the user's sleep quality. Other embodiments are described and claimed.

Abstract: Embodiments of the invention describe a system to efficiently execute gesture recognition algorithms. Embodiments of the invention describe a power efficient staged gesture recognition pipeline including multimodal interaction detection, context based optimized recognition, and context based optimized training and continuous learning. Embodiments of the invention further describe a system to accommodate many types of algorithms depending on the type of gesture that is needed in any particular situation. Examples of recognition algorithms include but are not limited to, HMM for complex dynamic gestures (e.g. write a number in the air), Decision Trees (DT) for static poses, peak detection for coarse shake/whack gestures or inertial methods (INS) for pitch/roll detection.

Abstract: Systems, devices, and techniques are provided for occupancy assessment of a vehicle. For one or more occupants of the vehicle, the occupancy assessment establishes position and/or identity for some or all of the occupant(s).

Abstract: Technologies for representing alternate reality characters in a real-world environment include receiving sensor data from sensors of a sensor network of a home location of an alternate reality character, determining available response to the stimuli represented by the sensor data, and determining an activity of the alternate reality character for a time period based on the available responses. The technologies may also include generating a video of the alternate reality character performing the determined activity superimposed on an image map of a real-world environment of the home location during the time period. Users may view the video in real time or during a time period subsequent to the time period represented in the video. Additionally, the alternate reality character may be transferred to remote computing devices in some embodiments.

Abstract: Language education systems capable of integrating with a user's daily life and automatically producing educational prompts would be particularly advantageous. An example method includes determining a user's identity, detecting a language education subject, prompting the user with a language education message, receiving a user's response, and updating a user profile associated with the user based on the user's response. Methods may also include determining user state (including emotional, physical, social, etc.) and determining, based on the user state, whether to prompt the user with the language education prompt.