Abstract: Disclosed are an audio synchronous circuit and an audio synchronous method. The audio synchronous circuit receives at least one beacon packet to generate WiFi time synchronization function (TSF) data, compares the WiFi TSF data with I2S TSF data according to a synchronous control signal to obtain a frequency offset, and compensates a digital audio clock according to the frequency offset. Thus, the audio synchronous circuit can adjust a frequency of the digital audio clock according to the frequency offset to complete synchronization with a transmitter, to avoid unpredictable delays caused by software processing and wireless channel competition, and achieve the purpose of more accurate time synchronization.

Abstract: A matrix multiplier includes an operation circuit and a controller. The operation circuit is coupled to the controller. The controller is configured to control the operation circuit to reuse a left fractal matrix Asr in n consecutive clock cycles, and control the operation circuit to use a right fractal matrix Brt in n right fractal matrices in each of the n consecutive clock cycles. The operation circuit is configured to multiply, in each of the n consecutive clock cycles, the left fractal matrix by the right fractal matrix in the n right fractal matrices to obtain n matrix operation results.

Abstract: A method for distributing an equity reward for federated learning based on an equity theory includes the following steps: applying Adams' equity theory to federated learning, analyzing, by a participant, all factors invested in a federated task comprehensively, then giving an expected reward for this task, calculating, by the task publisher, the reputation of the participant; participating, by the participant, in each round of a training task using a local data to evaluate data contribution, model contribution, and a waiting-time allowance of the participant, then combining contribution results of the three factors to evaluate the contribution of the participant; after a global model converges, dynamically adjusting weights of the three factors according to an objective function of the equity reward, with a goal that an actual reward of the participant is as close as possible to the expected reward, and obtaining and distributing the actual reward of the participant.

Abstract: A method for distributing an equity reward for federated learning based on an equity theory includes the following steps: applying Adams' equity theory to federated learning, analyzing, by a participant, all factors invested in a federated task comprehensively, then giving an expected reward for this task, calculating, by the task publisher, the reputation of the participant; participating, by the participant, in each round of a training task using a local data to evaluate data contribution, model contribution, and a waiting-time allowance of the participant, then combining contribution results of the three factors to evaluate the contribution of the participant; after a global model converges, dynamically adjusting weights of the three factors according to an objective function of the equity reward, with a goal that an actual reward of the participant is as close as possible to the expected reward, and obtaining and distributing the actual reward of the participant.