To deal with too many parameters and too much computation in Deep Neural Networks （DNNs）， an unlabeled neural network pruning algorithm based on Bayesian optimization was proposed. Firstly， based on a global pruning strategy， the sub-optimal compression ratio of the model caused by layer-by-layer pruning was avoided effectively. Secondly， the pruning process was independent on the labels of data samples， and the compression ratios of all layers were optimized by minimizing the distance between the output features of pruning and baseline networks. Finally， the Bayesian optimization algorithm was adopted to find the optimal compression ratio of each layer， thereby improving the efficiency and accuracy of sub-network search. Experimental results show that when compressing VGG-16 network by the proposed algorithm on CIFAR-10 dataset， the parameter compression ratio is 85.32%， and the Floating Point of Operations （FLOPS） compression ratio is 69.20% with only 0.43% accuracy loss. Therefore， the DNN model can be compressed effectively by the proposed algorithm， and the compressed model can still maintain good accuracy.

Through the analysis of the LTE system in FPGA-based spatial multiplexing coding problem, and propose a implementation of a codebook-based precoding. According to the parameters of the upper informed carries on the table look-up in the mathematical table and the addition and subtraction relations table, the data of layer mapping first carries on coefficient multiplication, then add and subtract, thus this has replaced the complex matrix multiplication operation. Therefore this method can greatly reduce the complex matrix multiplication operation in the precoding procedure, and reduce the complexity of encoding process, improve the speed of the encoding operation. The experimental results indicate that the proposed algorithm can achieve a good system function.