Abstract: A system includes a processor that executes computer executable components stored in a memory. The computer executable components can include a reception component that receives a query. The computer executable components can further include a contextualization component that contextualizes the query by identifying context of the query and summarizing background information of the query. The computer executable components can further include a keyword extraction component that uses a natural language processor to identify keywords of the contextualized query. Additionally, the computer executable components can include a refinement component that generates a new query based at least in part on the summarized background information and the extracted keywords. The computer executable components can further include an execution component that uses a retrieval-augmented generation system to run the new query.

Abstract: The disclosure relates to in-ear electronic devices. According to one aspect, the in-ear electronic device comprises a housing shaped to be inserted into an ear canal of a human, a set of electrodes configured to sense electrical signals when the housing is inserted into the ear canal, an antenna, a radio frequency (RF) transceiver, an audio transducer, and a control circuit. The control circuit is configured to provide an audio signal to the audio transducer based on an input RF signal received on the antenna, wherein the audio transducer plays the audio signal into the ear canal. The control circuit is configured to form an output signal based on one or more electrical signals from the set of electrodes. The control circuit is configured to passively backscatter the input RF signal on the antenna based on the output signal to wirelessly transmit the output signal.

Abstract: The present technology discloses a frameless modular multi-functional electronic device. The electronic device includes a base module with a processor and multiple component modules, at least one of which is configured to connect directly in contact with the base module. The modules each include a connecting member to slidably align and mate the component modules together, and an electrical interface to transmit digital information and energy between connected base and component modules. The component modules are interchangeably connected directly in contact with each other and, when assembled, form the frameless modular multi-functional electronic device.

Abstract: A method implemented by an agent monitoring device, comprises obtaining, by a sensor of the agent monitoring device, sensor data over a period of time, the sensor data describing a characteristic of an agent associated with the agent monitoring device, determining output data for the sensor based on the sensor data using a learning model, determining a sensor condition for the sensor, determining that a power level of a battery of the agent monitoring device meets the pre-defined power level, determining whether the output data meets the threshold value of the sensor condition in response to the power level of the battery having reached the pre-defined power level, and uploading an indication of the output data to at least one of a cloud server or a representative device in response to the output data for the sensor having met the threshold value of the sensor condition.

Abstract: In a method for improving converter and compiler operator granularity, a processor extracts an operator granularity from an artificial intelligence framework and an original model. A processor receives device characteristics from a target device. A processor outputs a converter granularity level to a converter based on the operator granularity and the device characteristics. A processor outputs a compiler granularity level to a compiler based on the operator granularity and the device characteristics.

Abstract: The present technology discloses communication in a communications network. A source node receives a media file from a client device in the communications network. Contextual information in the file is obtained that is descriptive of content in the medial file. When a match to the media file is found, the contextual information is accessed from storage. Otherwise, the contextual information is generated by the source node by extracting attributes from metadata in the media file. The media file is then transmitted over a first data path, and the contextual information is transmitted over a second data path, where the first data path has a higher latency than the second data path such that the contextual information arrives at the destination node prior to the media file.

Abstract: Aspects of the invention include converting an artificial intelligence (AI) model generated in a first framework to a uniform exchange formatted model by engaging a master table to retrieve instructions for converting from the AI model to the uniform exchange formatted model in accordance with the first framework. The uniform exchange formatted model in compiled by engaging the master table to retrieve instructions for compiling the uniform exchange formatted model in accordance with the first framework. Data is received as an input to the compiled uniform exchange formatted model and an output is generated by engaging the master table to retrieve instructions for generating the output in accordance with the first framework.

Abstract: The present technology discloses storing data in a peer-to-peer network. A first computing device identifies other computing devices in the peer-to-peer network. Each of the computing devices have an established social relationship with at least another one of the computing devices. A degree of connection between the first computing device and each of the other computing devices is detected. A group of the other of computing devices is selected based on the degree of connection for storing the data, and a storage trust level is assigned to each of the other computing devices in the group. The storage trust level of each of the other computing devices is based on the established social relationship. The data is then transmitted to each of the other computing devices in the group for storage.

Abstract: An electronic device includes a memory; and a processor coupled to the memory and configured to receive instructions from the memory which, when executed by the processor, cause the electronic device to transmit first data associated with a first blockchain to a second application; receive second data associated with a second blockchain from the second application; transmit the first data to a middleware smart contract; perform a first blockchain function using the first data and the second data to obtain a first result; receive third data from the middleware smart contract in response to transmission of the first data to the middleware smart contract; trust the middleware smart contract when the first result and third data match; and generate an alert when the first result and the third data do not match.

Abstract: The present technology discloses communication in a communications network. A source node receives a media file from a client device in the communications network. Contextual information in the file is obtained that is descriptive of content in the medial file. When a match to the media file is found, the contextual information is accessed from storage. Otherwise, the contextual information is generated by the source node by extracting attributes from metadata in the media file. The media file is then transmitted over a first data path, and the contextual information is transmitted over a second data path, where the first data path has a higher latency than the second data path such that the contextual information arrives at the destination node prior to the media file.

Abstract: The present technology discloses a frameless modular multi-functional electronic device. The electronic device includes a base module with a processor and multiple component modules, at least one of which is configured to connect directly in contact with the base module. The modules each include a connecting member to slidably align and mate the component modules together, and an electrical interface to transmit digital information and energy between connected base and component modules. The component modules are interchangeably connected directly in contact with each other and, when assembled, form the frameless modular multi-functional electronic device.

Abstract: The disclosure relates to in-ear electronic devices. According to one aspect, the in-ear electronic device comprises a housing shaped to be inserted into an ear canal of a human, a set of electrodes configured to sense electrical signals when the housing is inserted into the ear canal, an antenna, a radio frequency (RF) transceiver, an audio transducer, and a control circuit. The control circuit is configured to provide an audio signal to the audio transducer based on an input RF signal received on the antenna, wherein the audio transducer plays the audio signal into the ear canal. The control circuit is configured to form an output signal based on one or more electrical signals from the set of electrodes. The control circuit is configured to passively backscatter the input RF signal on the antenna based on the output signal to wirelessly transmit the output signal.

Abstract: The present technology discloses a federated learning network including a server and multiple client devices. The server receives a set of parameters of a local machine-learning model from each client device in a subset of the multiple client devices. The set of parameters are combined from each of the client devices in the subset to generate an integrated set of parameters. The server then calculates a parameter difference between the integrated set of parameters and the set of parameters for each client device in the subset. Feedback is sent by the server to each client device in the subset. The feedback is applied during backpropagation of the client. If the local parameters of a client are determined to be invalid for a number of times, the client will be set as an outlier.

Abstract: The present technology discloses storing data in a peer-to-peer network. A first computing device identifies other computing devices in the peer-to-peer network. Each of the computing devices have an established social relationship with at least another one of the computing devices. A degree of connection between the first computing device and each of the other computing devices is detected. A group of the other of computing devices is selected based on the degree of connection for storing the data, and a storage trust level is assigned to each of the other computing devices in the group. The storage trust level of each of the other computing devices is based on the established social relationship. The data is then transmitted to each of the other computing devices in the group for storage.

Abstract: Techniques are presented to improve the security of operation for autonomously driving automobiles and other transportation or robotic equipment with varying degrees of autonomous operation. This can include an end-to-end closed-system support of control sensors' own signal emission and self-controlled frequency or polarization, which can be hard to decipher by external attackers. The control systems can employ majority voting by multiple perception results from both time (e.g., samples from same polarization in time series of an epoch, given the fact of oversampling) and space (e.g., different polarizations or sensor types) domains for enhanced security.

Abstract: Embodiments for locating performance hot spots include collecting sample data having instruction addresses, the sample data being for a neural network model and determining instructions in the instruction addresses that are performance hot spots. A listing file is used to map the instructions of the sample data that are performance hot spots to locations in a lower-level intermediate representation. A mapping file is used to map the locations of the lower-level intermediate representation that are performance hot spots to operations in one or more higher-level representations, one or more of the operations corresponding to the performance hot spots, the mapping file being generated from compiling the neural network model.

Abstract: A method of training a large neural network using a number of pre-trained smaller neural networks. Multiple pre-existing, pre-trained neural networks are used to create the large neural network using multi-level superposition. The pre-trained neural networks, each having a first number of multi-dimensional nodes, are each up-scaled to provide larger, sparse neural networks. The values of the larger, sparse neural networks are superpositioned into the larger neural network. The pre-trained neural networks may be created from publicly available, pre-trained neural networks. The larger neural network can be adapted for use in a different task by replacing and/or re-training one of the sub-networks used to create the large neural network.

Abstract: The disclosure relates to technology for acceleration of GPUs in cloud. Instructions for a computational task are accessed. An allocation of data and instructions is calculated based on the data, the instructions, and dynamic GPU resources. The data and the instructions are provided to the GPUs in accordance with the allocation, which includes scheduling a set of instructions for parallel computation of an operation of the computational task on multiple sub-matrices of a data matrix. Separate portions of information are stored into corresponding different regions of non-transitory memory of a processor core to provide concurrent access to the multiple sub-matrices to the processor core. Each sub-matrix corresponds to a portion of the data matrix for which an operation of the computational task is to be performed. Each sub-matrix contains an element in the data matrix in common with another sub-matrix of the data matrix.

Abstract: A method implemented by an agent monitoring device, comprises obtaining, by a sensor of the agent monitoring device, sensor data over a period of time, the sensor data describing a characteristic of an agent associated with the agent monitoring device, determining output data for the sensor based on the sensor data using a learning model, determining a sensor condition for the sensor, determining that a power level of a battery of the agent monitoring device meets the pre-defined power level, determining whether the output data meets the threshold value of the sensor condition in response to the power level of the battery having reached the pre-defined power level, and uploading an indication of the output data to at least one of a cloud server or a representative device in response to the output data for the sensor having met the threshold value of the sensor condition.