Abstract: A wood-plastic/lumber composite co-extrusion feeder includes a frame, wherein at least one group of toothed conveying units, a tooth mark milling unit for milling tooth marks on an outer surface of a lumber, and a lumber co-extrusion mold are arranged on the frame in sequence, each toothed conveying unit includes a lower toothed pressure roller installed on a first fixed bearing seat and an upper toothed pressure roller installed on a first movable bearing seat, and after the first fixed bearing seat and the first movable bearing seat are connected by an adjustment unit, a first conveying channel having an adjustable height is formed between the upper toothed pressure roller and the lower-toothed pressure roller.

Abstract: A method for evaluating robustness of one or more target neural network models using natural typos. The method includes receiving one or more natural typo generation rules associated with a first task associated with a first input document type, receiving a first target neural network model, and receiving a first document and corresponding its ground truth labels. The method further includes generating one or more natural typos for the first document based on the one or more natural typo generation rules, and providing, to the first target neural network model, a test document generated based on the first document and the one or more natural typos as an input document to generate a first output. A robustness evaluation result of the first target neural network model is generated based on a comparison between the output and the ground truth labels.

Abstract: Systems and methods are provided for near-zero-cost (NZC) query framework or approach for differentially private deep learning. To protect the privacy of training data during learning, the near-zero-cost query framework transfers knowledge from an ensemble of teacher models trained on partitions of the data to a student model. Privacy guarantees may be understood intuitively and expressed rigorously in terms of differential privacy. Other features are also provided.

Abstract: A method for training parameters of a student model includes receiving one or more teacher models trained using sensitive data. Each teacher model includes one or more intermediate layers and a prediction layer coupled to the one or more intermediate layers. The method includes receiving, from the one or more teacher models, one or more intermediate layer outputs and one or more prediction layer outputs respectively based on public data. Student model training is performed to train parameters of the student model based on the intermediate layer outputs and prediction layer outputs of the one or more teacher models.

Abstract: Approaches for private and interpretable machine learning systems include a system for processing a query. The system includes one or more teacher modules for receiving a query and generating a respective output, one or more privacy sanitization modules for privacy sanitizing the respective output of each of the one or more teacher modules, and a student module for receiving a query and the privacy sanitized respective output of each of the one or more teacher modules and generating a result. Each of the one or more teacher modules is trained using a respective private data set. The student module is trained using a public data set. In some embodiments, human understandable interpretations of an output from the student module is provided to a model user.

Abstract: In one embodiment, a method includes accessing a plurality of initial gradients associated with a machine-learning model from a data store associated with a first electronic device, selecting one or more of the plurality of initial gradients for perturbation, generating one or more perturbed gradients for the one or more selected initial gradients based on a gradient-perturbation model, respectively, wherein for each selected initial gradient: an input to the gradient-perturbation model comprises the selected initial gradient having a value x, the gradient-perturbation model changes x into a first continuous value with a first probability or a second continuous value with a second probability, and the first and second probabilities are determined based on x, and sending the one or more perturbed gradients from the first electronic device to a second electronic device.

Abstract: Provided are a preparation method of pyrrolo-amino-pyridazinone compound and an intermediate thereof. The reaction conditions are easy to control, the processing following the reaction is simple, the production rate is high, and the method is advantageous for industrial production.

Abstract: A wood-plastic/lumber composite co-extrusion feeder includes a frame, wherein at least one group of toothed conveying units, a tooth mark milling unit for milling tooth marks on an outer surface of a lumber, and a lumber co-extrusion mold are arranged on the frame in sequence, each toothed conveying unit includes a lower toothed pressure roller installed on a first fixed bearing seat and an upper toothed pressure roller installed on a first movable bearing seat, and after the first fixed bearing seat and the first movable bearing seat are connected by an adjustment unit, a first conveying channel having an adjustable height is formed between the upper toothed pressure roller and the lower-toothed pressure roller.

Abstract: Systems and methods are provided for near-zero-cost (NZC) query framework or approach for differentially private deep learning. To protect the privacy of training data during learning, the near-zero-cost query framework transfers knowledge from an ensemble of teacher models trained on partitions of the data to a student model. Privacy guarantees may be understood intuitively and expressed rigorously in terms of differential privacy. Other features are also provided.

Abstract: A method for evaluating robustness of one or more target neural network models using natural typos. The method includes receiving one or more natural typo generation rules associated with a first task associated with a first input document type, receiving a first target neural network model, and receiving a first document and corresponding its ground truth labels. The method further includes generating one or more natural typos for the first document based on the one or more natural typo generation rules, and providing, to the first target neural network model, a test document generated based on the first document and the one or more natural typos as an input document to generate a first output. A robustness evaluation result of the first target neural network model is generated based on a comparison between the output and the ground truth labels.

Abstract: A method for training parameters of a student model includes receiving one or more teacher models trained using sensitive data. Each teacher model includes one or more intermediate layers and a prediction layer coupled to the one or more intermediate layers. The method includes receiving, from the one or more teacher models, one or more intermediate layer outputs and one or more prediction layer outputs respectively based on public data. Student model training is performed to train parameters of the student model based on the intermediate layer outputs and prediction layer outputs of the one or more teacher models.

Abstract: Approaches for private and interpretable machine learning systems include a system for processing a query. The system includes one or more teacher modules for receiving a query and generating a respective output, one or more privacy sanitization modules for privacy sanitizing the respective output of each of the one or more teacher modules, and a student module for receiving a query and the privacy sanitized respective output of each of the one or more teacher modules and generating a result. Each of the one or more teacher modules is trained using a respective private data set. The student module is trained using a public data set. In some embodiments, human understandable interpretations of an output from the student module is provided to a model user.