Abstract:
An electronic device for performing sensitivity-based quantized training and an operating method thereof is disclosed. The electronic device includes a processor, and a memory configured to store instructions executable by the processor, wherein the processor is configured to, in response to the instructions being executed by the processor, generate, based on a determination of sensitivity of layers in a model to be trained, sensitivity results, and train the model by applying quantization to a layer of the layers with a low sensitivity of the sensitivity results lower than a predetermined threshold.
Abstract:
A processor-implemented data processing method includes: normalizing input data of an activation function comprising a division operation; determining dividend data corresponding to a dividend of the division operation by reading, from a memory, a value of a first lookup table addressed by the normalized input data; determining divisor data corresponding to a divisor of the division operation by accumulating the dividend data; and determining output data of the activation function corresponding to an output of the division operation obtained by reading, from the memory, a value of a second lookup table addressed by the dividend data and the divisor data.
Abstract:
An electronic device includes a biomedical sensor configured to generate a first signal by detecting a biomedical signal, a motion sensor configured to generate a second signal by detecting a motion, and a communication interface configured to provide a secure communication channel with another electronic device, and receive a third signal through the secure communication channel. The electronic device further includes a controller configured to generate a secret key for the secure communication channel, based on the first signal, and determine whether to perform a predetermined function, based on the second signal and the received third signal.
Abstract:
A random number health test method according to the inventive concepts including generating a random number, counting occurrences of at least two words in the generated random number, respectively, calculating probability values corresponding to occurrences of the two counted words; calculating minimum entropies (Hmin) of the respective probability values, and determining health of the generated random numbers using the calculated minimum entropies (Hmin) may be provided.