Abstract:
Certain aspects of the present disclosure provide techniques for improved machine learning using gradient pruning, comprising computing, using a first batch of training data, a first gradient tensor comprising a gradient for each parameter of a parameter tensor for a machine learning model; identifying a first subset of gradients in the first gradient tensor based on a first gradient criteria; and updating a first subset of parameters in the parameter tensor based on the first subset of gradients in the first gradient tensor.
Abstract:
A method for pruning weights of an artificial neural network based on a learned threshold includes determining a pruning threshold for pruning a first set of pre-trained weights of multiple pre-trained weights based on a function of a classification loss and a regularization loss. The first set of pre-trained weights is pruned in response to a first value of each pre-trained weight in the first set of pre-trained weights being greater than the pruning threshold. A second set of pre-trained weights of the multiple pre-trained weights is fine-tuned or adjusted in response to a second value of each pre-trained weight in the second set of pre-trained weights being greater than the pruning threshold.
Abstract:
Methods, systems, and devices are described for using information relating to a motion state of a mobile device to inform a handover decision of the mobile device. In one aspect, a method may include obtaining motion state information of the mobile device and, based on the motion state information, generating predictive information, for example relating to whether the mobile device is moving out of a network coverage area, such as a WLAN, to a WWAN or another WLAN. The mobile device may then participate in a handover based on the predictive information. In one aspect, the mobile device may participate in the handover prior to disconnection with a serving network and/or prior to a connection quality with the serving network falling below a connection quality threshold.
Abstract:
Systems and methods share context information on a neighbor aware network. A method for communicating data in a wireless communications network is disclosed. The method includes receiving, by a device, a first message from a station, decoding the message to determine service information, the service information identifying a service provided by the station, generating a second message, wherein the second message is generated to indicate the service provided by the station and service information of the device, and transmitting, by the device, the second message to a remote station.
Abstract:
A method for pruning weights of an artificial neural network based on a learned threshold includes designating a group of pre-trained weights of an artificial neural network to be evaluated for pruning. The method also includes determining a norm of the group of pre-trained weights, and performing a process based on the norm to determine whether to prune the entire group of pre-trained weights.
Abstract:
Disclosed are techniques for determining a severity of motion disorder symptoms by receiving sensor data from one or more sensors, determining that the sensor data represents one or more activities of daily life (ADLs) of a user, assigning one or more probabilities to the one or more determined ADLs, each probability of the one or more probabilities indicating a confidence level that the sensor data represents a corresponding ADL, and providing the sensor data and the one or more probabilities to a motion disorder symptom scoring module that generates one or more scores for the one or more determined ADLs based on the sensor data, each score of the one or more scores indicating the severity of the motion disorder symptoms for a corresponding ADL, and combines the one or more scores and the one or more probabilities to generate an aggregated severity score for the motion disorder symptoms.
Abstract:
Methods, systems, computer-readable media, and apparatuses for calendar matching of inferred contexts are described. In one potential embodiment, a mobile device may use context information to generate a calendar of inferred contexts. Label information from raw calendar data may be used to update an inferred context within a calendar of inferred contexts. Additionally, the label may be propagated to future contexts and entries in an inferred context calendar.
Abstract:
A system and method are disclosed that may selectively switch a station's association from a first AP to a second AP based, at least in part, on whether an indication of first RSSI values for the first AP is greater than an indication of second RSSI values for the second AP by more than a difference value. For some embodiments, the difference value may be dynamically adjusted based, at least in part, on the first RSSI values, on a connection history of the station, and/or on a user selection.
Abstract:
The disclosure is directed to using motion to reduce unnecessary scans for local wireless networks. An aspect determines whether or not a motion state change event of a user device indicates a change from a moving motion state to a stationary motion state, and if the motion state change event indicates a change from a moving motion state to a stationary motion state, ignoring the motion state change event. An aspect of the disclosure is directed to using motion to reduce latency of scanning for local wireless networks. An aspect determines whether or not a user device is in motion, determines whether or not a periodic scan timer has expired and/or a received signal strength indicator (RSSI) is below a threshold, and if the user device is in motion and the periodic scan timer has expired or the RSSI is below the threshold, scanning for a local wireless network.
Abstract:
Systems and methods share context information on a neighbor aware network. In one aspect, a context providing device receives a plurality of responses to a discovery query from a context consuming device, and tailors services it offers to the context consuming device based on the responses. In another aspect, a context providing device indicates in its response to a discovery query which services or local context information it can provide to the context consuming device, and also a cost associated with providing the service or the local context information. In some aspects, the cost is in units of monetary currency. In other aspects, the cost is in units of user interface display made available to an entity associated with the context providing device in exchange for the services or local context information offered to the context consuming device.