Abstract: Model training systems collaborate on model training without revealing respective private data sets. Each private data set learns a set of client weights for a set of computer models that are also learned during training. Inference for a particular private data set is determined as a mixture of the computer model parameters according to the client weights. During training, at each iteration, the client weights are updated in one step based on how well sampled models represent the private data set. In another step, gradients are determined for each sampled model and may be weighed according to the client weight for that model, relatively increasing the gradient contribution of a private data set for model parameters that correspond more highly to that private data set.

Abstract: An improved computer implemented method and corresponding systems and computer readable media for improving performance of a deep neural network are provided to mitigate effects related to catastrophic forgetting in neural network learning. In an embodiment, the method includes storing, in memory, logits of a set of samples from a previous set of tasks (D1); and maintaining classification information from the previous set of tasks by utilizing the logits for matching during training on a new set of tasks (D2).

Abstract: A model training system protects data leakage of private data in a federated learning environment by training a private model in conjunction with a proxy model. The proxy model is trained with protections for the private data and may be shared with other participants. Proxy models from other participants are used to train the private model, enabling the private model to benefit from parameters based on other models’ private data without privacy leakage. The proxy model may be trained with a differentially private algorithm that quantifies a privacy cost for the proxy model, enabling a participant to measure the potential exposure of private data and drop out. Iterations may include training the proxy and private models and then mixing the proxy models with other participants. The mixing may include updating and applying a bias to account for the weights of other participants in the received proxy models.

Abstract: An improved computer implemented method and corresponding systems and computer readable media for improving performance of a deep neural network are provided to mitigate effects related to catastrophic forgetting in neural network learning. In an embodiment, the method includes storing, in memory, logits of a set of samples from a previous set of tasks (D1); and maintaining classification information from the previous set of tasks by utilizing the logits for matching during training on a new set of tasks (D2).

Abstract: A transconductance-enhancing passive frequency mixer comprises a transconductance amplification stage, a frequency mixing stage, and an output transresistance amplifier. The transconductance amplification stage has a pre-amplification transconductance-enhancing structure, so that the transconductance is greatly enhanced, thereby obtaining the same transconductance value at a lower bias current. A radio-frequency current is modulated by the frequency mixing stage to generate an output mid-frequency current signal. The mid-frequency current signal passes through the transresistance amplifier, to form voltage output, and finally obtain a mid-frequency voltage signal. The transresistance amplifier has a transconductance-enhancing structure, thereby further reducing input impedance, and improving current utilization efficiency and port isolation. The frequency mixer has the characteristics of low power consumption, high conversion gain, good port isolation, and the like.

Abstract: A transconductance-enhancing passive frequency mixer comprises a transconductance amplification stage, a frequency mixing stage, and an output transresistance amplifier. The transconductance amplification stage has a pre-amplification transconductance-enhancing structure, so that the transconductance is greatly enhanced, thereby obtaining the same transconductance value at a lower bias current. A radio-frequency current is modulated by the frequency mixing stage to generate an output mid-frequency current signal. The mid-frequency current signal passes through the transresistance amplifier, to form voltage output, and finally obtain a mid-frequency voltage signal. The transresistance amplifier has a transconductance-enhancing structure, thereby further reducing input impedance, and improving current utilization efficiency and port isolation. The frequency mixer has the characteristics of low power consumption, high conversion gain, good port isolation, and the like.