Search

Abstract:Due to their superior performance, deep neural networks have been widely applied in fields such as image recognition and object detection. However, they contain a large number of parameters and require immense computational power, posing challenges for deployment on mobile edge devices that require low latency and low power consumption. To address this issue, a compression algorithm that replaces multiplication operations with bit-shifting and addition is proposed. This algorithm compresses neural network parameters to low bit-widths through pruning and quantization. This algorithm reduces the hardware deployment difficulty under limited multiplication resources, meets the requirements of low latency and low power consumption on mobile edge devices, and improves operational efficiency. Experiments conducted on classical neural networks with the ImageNet dataset revealed that when the neural network parameters were compressed to 4 bits, the accuracy remained essentially unchanged compared to the full-precision neural network. Furthermore, for ResNet18, ResNet50, and GoogleNet, the Top-1/Top-5 accuracies even improved by 0.38%/0.22%, 0.35%/0.21%, and 1.14%/0.57%, respectively. When testing the eighth convolutional layer of VGG16 deployed on Zynq7035, the results showed that the compressed network reduced the inference time by 51.1% and power consumption by 46.7%, while using 43% fewer DSP resources. [ABSTRACT FROM AUTHOR]

PTFE/Al reactive material is an energetic material that releases energy under impact conditions, resulting in a wide range of application prospects. In order to improve its damage ability—considering the higher heat of the reaction per unit mass when Ni2O3 is involved in the aluminothermic reaction—we designed and studied PTFE/Al/Ni2O3, a reaction material based on polytetrafluoroethylene (PTFE). We also designed two other kinds (PTFE/Al, PTFE/Al/CuO) for comparative study, with the mass fraction of the metal oxides added at 10%, 20%, and 30%, respectively. The quasi-static compression properties and impact initiation behavior of the material were investigated by a universal material testing machine and a drop hammer test. The reaction process of different materials under a high strain rate was recorded using a high-speed camera. The results show that with the increase in Ni2O3 content, the strength of the PTFE/Al/Ni2O3 reactive material shows an increasing trend followed by a decreasing trend. Among the three reactive materials, when the content of Al/Ni2O3 reaches 30 wt.%, the reaction duration is the longest (at 4 ms) and the reaction fireball is the largest. The addition of Ni2O3 is helpful to improve the reactivity and reaction duration of the PTEF/Al reactive material. [ABSTRACT FROM AUTHOR]