Abstract: The present application provides a preparation method for a core-shell structured tungsten/gadolinium oxide functional fiber for X and ? ray protection, comprising: first preparing a core-shell structured tungsten/gadolinium oxide powder; preparing a W@Gd2O3/PP blended melt from the powder; and preparing a W@Gd2O3/PP composite fiber from the blended melt. The core-shell structured tungsten/gadolinium oxide functional fiber prepared by the method can play a role in synergistic protection in the aspect of radiation protection, eliminate a weak protection area, and effectively absorb secondary radiation generated by radiation. Secondly, the prepared functional fiber has the characteristics of no lead and light weight, and has good application prospects in the aspect of X and ? ray radiation protection.

Abstract: A dust-collecting box includes a dust-collecting box body and a filter screen. The dust-collecting box body defines a dust inlet, a dust receiving cavity and an exhaust passage which are communicated in sequence, an air inlet end of the exhaust passage is in communication with the dust receiving cavity, and an air outlet end of the exhaust passage is in pneumatic communication with a fan assembly. The filter screen is arranged between the air inlet end and the air outlet end, the filter screen filters an airflow entering the exhaust passage from the dust receiving cavity, an exhaust direction of the air outlet end is defined as a preset reference direction, and the filter screen is arranged obliquely relative to the preset reference direction.

Abstract: Interpretation maps of convolutional neural networks having certifiable robustness using Rényi differential privacy are provided. In one aspect, a method for generating an interpretation map includes: adding generalized Gaussian noise to an image x to obtain T noisy images, wherein the generalized Gaussian noise constitutes perturbations to the image x; providing the T noisy images as input to a convolutional neural network; calculating T noisy interpretations of output from the convolutional neural network corresponding to the T noisy images; re-scaling the T noisy interpretations using a scoring vector ? to obtain T re-scaled noisy interpretations; and generating the interpretation map using the T re-scaled noisy interpretations, wherein the interpretation map is robust against the perturbations.

Abstract: Interpretation maps of deep neural networks are provided that use Renyi differential privacy to guarantee the robustness of the interpretation. In one aspect, a method for generating interpretation maps with guaranteed robustness includes: perturbing an original digital image by adding Gaussian noise to the original digital image to obtain m noisy images; providing the m noisy images as input to a deep neural network; interpreting output from the deep neural network to obtain m noisy interpretations corresponding to the m noisy images; thresholding the m noisy interpretations to obtain a top-k of the m noisy interpretations; and averaging the top-k of the m noisy interpretations to produce an interpretation map with certifiable robustness.

Abstract: Interpretation maps of convolutional neural networks having certifiable robustness using Rényi differential privacy are provided. In one aspect, a method for generating an interpretation map includes: adding generalized Gaussian noise to an image x to obtain T noisy images, wherein the generalized Gaussian noise constitutes perturbations to the image x; providing the T noisy images as input to a convolutional neural network; calculating T noisy interpretations of output from the convolutional neural network corresponding to the T noisy images; re-scaling the T noisy interpretations using a scoring vector ? to obtain T re-scaled noisy interpretations; and generating the interpretation map using the T re-scaled noisy interpretations, wherein the interpretation map is robust against the perturbations.

Abstract: Interpretation maps of deep neural networks are provided that use Renyi differential privacy to guarantee the robustness of the interpretation. In one aspect, a method for generating interpretation maps with guaranteed robustness includes: perturbing an original digital image by adding Gaussian noise to the original digital image to obtain m noisy images; providing the m noisy images as input to a deep neural network; interpreting output from the deep neural network to obtain m noisy interpretations corresponding to the m noisy images; thresholding the m noisy interpretations to obtain a top-k of the m noisy interpretations; and averaging the top-k of the m noisy interpretations to produce an interpretation map with certifiable robustness.