No abstract

The traditional data automatic office system has limited mining and computing capabilities. Due to the iterative complexity of data mining algorithms, it is difficult to discover the relationships and rules existing in the Internet of Things data as well as impossible to advance the efficiency of the office system based on the existing Internet of Things data. This paper combines cloud computing and machine learning to construct an intelligent network office system, realizes large-scale IoT data processing through the combination of IoT data mining technology and cloud computing framework, and constructs the functional module structure of the intelligent network office system through demand analysis. On this basis, this paper conducts system performance verification and conducts experimental design based on network intelligent system demand. The experimental results show that the system constructed in this paper has certain practical effects, which can provide theoretical reference for subsequent related research.

Convolutional Neural Network (CNN) has an amount of parameter redundancy, filter pruning aims to remove the redundant filters and provides the possibility for the application of CNN on terminal devices. However, previous works pay more attention to designing evaluation criteria of filter importance and then prune less important filters with a fixed pruning rate or a fixed number to reduce convolutional neural networks' redundancy. It does not consider how many filters to reserve for each layer is the most reasonable choice. From this perspective, we propose a new filter pruning method by searching the proper number of filters (SNF). SNF is dedicated to searching for the most reasonable number of reserved filters for each layer and then pruning filters with specific criteria. It can tailor the most suitable network structure at different FLOPs. Filter pruning with our method leads to the state-of-the-art (SOTA) accuracy on CIFAR-10 and achieves competitive performance on ImageNet ILSVRC-2012. SNF based on the ResNet-56 network achieves an increase of 0.14% in Top-1 accuracy at 52.94% FLOPs reduction on CIFAR-10. Pruning ResNet-110 on CIFAR-10 also improves the Top-1 accuracy of 0.03% when reducing 68.68% FLOPs. For ImageNet, we set the pruning rates as 52.10% FLOPs, and the Top-1 accuracy only has a drop of 0.74%. The codes can be available at https://github.com/pk-l/SNF.

No abstract