7results about How to "Mitigate performance degradation" patented technology

The application discloses a method for alleviating Non-IID influence based on explainable federated learning. The application mainly introduces a validation set explainable mechanism to depict the explainable results of the validation set samples in the center server based on the influence of local client update on the learning ability of each category of the aggregated model, and evaluates the explainable results of each category by using a structural similarity index (SSIM), so as to deduce the data imbalance clients. Then, the parameters of the data imbalance clients are adjusted, the gradient distance between the model of the data imbalance client and the parameter of the global aggregated model in the last round is minimized, and the parameters of the model of the data imbalance client are corrected through the convergence of the gradient distance, so that the negative influence caused by the data imbalance is weakened.

The application discloses an anti-poisoning attack cooperative security defense method and system for Internet of Vehicles, and relates to the technical field of Internet of Vehicles security. The method comprises the following steps: an initial model is issued by a cloud end to all vehicles at a vehicle end, vehicle end synchronously acquires in-vehicle network data and off-vehicle communication data, and performs preprocessing; the vehicle end trains and fine-tunes the received initial model with the minimum reconstruction error or feature space compactness loss as the target, and encrypts and updates the fine-tuned model based on privacy protection processing; the cloud end performs security screening on the encrypted and updated model parameters based on a multi-stage robust aggregation mechanism and a dynamic trust management model to obtain a global model; and the cloud end issues the global model and corresponding data to the vehicle end for real-time monitoring and feedback. The application can effectively resist malicious vehicle end attacks while guaranteeing vehicle data privacy and system real-time performance, and has strong cross-domain generalization capability.

The invention discloses a heterogeneous perception task scheduling method and system based on personalized federal reinforcement learning, and the method comprises the steps: constructing a task scheduling environment with a scene boundary based on load data, and constructing a local scheduling model based on the task scheduling environment through employing a dual-reviewer near-end strategy optimization algorithm; according to the method, public reviewer network model parameters in a constructed local scheduling model are aggregated, a personalized model is generated based on multi-head attention weights, and value estimation of local reviews and public reviews is fused by introducing Dual-Critic PPO, so that the problem of performance reduction of a global model in a heterogeneous environment is effectively relieved; and meanwhile, the stability of advantage estimation and the reliability of strategy updating are improved. According to the method, a server side carries out personalized aggregation on public reviewer parameters through a multi-head attention mechanism, so that different clients can obtain public models matched with environment characteristics of the clients instead of depending on a general average model, and thus faster convergence and stronger personalized adaptation are realized.

The present application relates to the field of handle error correction, and more particularly to a dynamic correction method and device for gamepad joystick offset error. The method comprises the following steps: detecting the player's no-input operation state, continuously collecting the original coordinate input value of the gamepad, and performing no-operation drift analysis to construct a static joystick dead zone; detecting the real-time operation signal stream of the player's handle, predicting the output behavior of the character in the scene, and generating game operation behavior data; based on the game operation behavior data, performing dynamic response deviation calculation, and constructing a handle drift vector field according to the static joystick dead zone; performing player operation intention analysis and unintended signal elimination processing on the real-time operation signal stream to obtain effective operation signals; performing reverse offset compensation calculation on the effective operation signals according to the handle drift vector field, and performing real-time joystick error correction. The present application corrects the signal recognition error of the gamepad, improves the response efficiency and accuracy of the game operation.

The application discloses a multilingual neural machine translation system using language family information, which is constructed based on a Transformer basic model, and a language family information module is added after each self-attention mechanism module and a feedforward neural network module in the Transformer basic model; the language family information module inputs language family information and the output of a preceding module, and outputs a vector after the language family information is fused. The application further provides a multilingual neural machine translation method using language family information. The multilingual neural machine translation system using language family information provided by the application alleviates the performance decline problem of large-scale multilingual machine translation on high-resource languages, and further improves the translation performance on low-resource languages.

Embodiments of the present disclosure provide an artificial intelligence chip, an artificial intelligence processor core and an electronic device. The artificial intelligence chip comprises a plurality of artificial intelligence processor cores and at least one communication chain, wherein the at least one communication chain comprises a first communication chain, the first communication chain sequentially connects the plurality of artificial intelligence processor cores in communication respectively, and comprises a plurality of first bidirectional communication units corresponding to the plurality of artificial intelligence processor cores respectively, each first bidirectional communication unit is connected in communication with a corresponding artificial intelligence processor core, and is configured to select a direction of data transmission of the corresponding artificial intelligence processor core through the first communication chain according to a received first control signal. The artificial intelligence chip can effectively solve the problem of system performance degradation caused by fixed direction communication bottleneck, and improve the overall efficiency of the artificial intelligence processor in processing complex workloads.