50 patents in CPC class G06N
A neural network retraining method based on the aging sensing of memristors is provided. For the accuracy rate of hardware online reasoning decreases after cross-array aging, the extreme values of programmable weights under a current aging condition is calculated by using the known aging information of memristor, and a neural network model is retrained according to this, so as to improve the accuracy rate of the current hardware online reasoning. In the process of retraining, network weights exceeding the extreme values of programmable weights are automatically truncated. For the working life of the memristor, the sparsity of derivatives of the neural network is utilized to discard the derivatives with a small absolute value in hardware adjustment process, so as to ensure that the memristor corresponding to small derivatives would not be applied voltage, prevent the aging process of the memristors and prolong the service life thereof.
Provided are a system and methodology for iteratively transforming data as between multiple sets thereof. Doing so, via normalization of the data, enables uniformity of interpretation and presentation of the data no matter the machine learning model that produced the data.
Electric charges depending on values of N+ electric signals and values of corresponding positive loads are held in first capture-and-storage circuitry. Electric charges having a size depending on values of (N−N+) electric signals and corresponding absolute values of negative loads are held in second capture-and-storage circuitry. A sum of N+ multiplied values obtained by multiplying each of the positive loads by each of the values of the N+ electric signals is calculated when a voltage held in the first capture-and-storage circuitry reaches a first threshold. A sum of (N−N+) multiplied values obtained by multiplying each of the absolute values by each of the values of the (N−N+) electric signals is calculated when a voltage held in the second capture-and-storage circuitry reaches a second threshold A sum of N multiplied values is obtained by subtracting the sum of (N−N+) multiplied values from the sum of N+ multiplied values.
Methods, systems, and media for recommending computerized services based on an animate object in the user's environment are provided. In some implementations, the method comprises: receiving a request from a user device to associate a recording device that captures motion data indicative of motion of an animate object in proximity to the user device; associating the user device with the recording device in response to receiving the request; receiving the motion data from the recording device that is indicative of motion of the animate object; determining characteristics of the animate object based on the received motion data; correlating an emotional state of a user of the user device based on the determined characteristics associated with the animate object; and causing a recommended computerized service to be presented by the user device based on the emotional state of the user.
A detection device that detects unauthorized communication in an on-vehicle network mounted on a vehicle includes: a monitoring unit that monitors first information that indicates a state or control related to the vehicle and that is transmitted in the on-vehicle network; a prediction unit that predicts an occurrence of second information in the on-vehicle network that indicates the state or control related to the vehicle based on the first information monitored by the monitoring unit; and a determination unit that determines, in a case where the second information is transmitted in the on-vehicle network, whether or not the transmitted second information is unauthorized, based on a result of prediction performed by the prediction unit.
A contaminated air exposure level inferring apparatus may include a receiver for receiving a fine dust concentration measured from a fine dust sensor of the wearable device or the portable air purifier, an exposure level classifier for inferring a contaminated air exposure level of a user holding the wearable device or the portable air purifier based on the measured fine dust concentration, and a communicator for communicating with a server. The server may include an artificial intelligence model learner for generating an artificial intelligence model that has learned data on the measured fine dust concentration through a deep neural network. According to the present disclosure, it is possible to infer the contaminated air exposure level of the user of the wearable device or the portable air purifier by using artificial intelligence (AI), a contaminated air exposure level inferring technology based on the artificial intelligence, and a 5G network.