Journal: Computational Intelligence and Neuroscience

Article Title: Optimizing the Deep Neural Networks by Layer-Wise Refined Pruning and the Acceleration on FPGA

doi: 10.1155/2022/8039281

Figure Lengend Snippet: CV of input sparsity. (a) ResNet50. (b) ResNet101. (c) VGG13BN.

Article Snippet: In this section, we deploy both the original and the pruned VGG13BN and ResNet101 trained on ImageNet100 on the Xilinx FPGA platform of Zynq UltraScale + MPSoC ZCU102 Evaluation Kit.

Techniques:

Journal: Computational Intelligence and Neuroscience

Article Title: Optimizing the Deep Neural Networks by Layer-Wise Refined Pruning and the Acceleration on FPGA

doi: 10.1155/2022/8039281

Figure Lengend Snippet: A “bottleneck” building block for ResNet101.

Article Snippet: In this section, we deploy both the original and the pruned VGG13BN and ResNet101 trained on ImageNet100 on the Xilinx FPGA platform of Zynq UltraScale + MPSoC ZCU102 Evaluation Kit.

Techniques: Blocking Assay

Journal: Computational Intelligence and Neuroscience

Article Title: Optimizing the Deep Neural Networks by Layer-Wise Refined Pruning and the Acceleration on FPGA

doi: 10.1155/2022/8039281

Figure Lengend Snippet: ResNet101 on CIFAR100-2.

Article Snippet: In this section, we deploy both the original and the pruned VGG13BN and ResNet101 trained on ImageNet100 on the Xilinx FPGA platform of Zynq UltraScale + MPSoC ZCU102 Evaluation Kit.

Techniques:

Journal: Computational Intelligence and Neuroscience

Article Title: Optimizing the Deep Neural Networks by Layer-Wise Refined Pruning and the Acceleration on FPGA

doi: 10.1155/2022/8039281

Figure Lengend Snippet: ResNet101 on CIFAR100-1.

Article Snippet: In this section, we deploy both the original and the pruned VGG13BN and ResNet101 trained on ImageNet100 on the Xilinx FPGA platform of Zynq UltraScale + MPSoC ZCU102 Evaluation Kit.

Techniques:

Journal: Computational Intelligence and Neuroscience

Article Title: Optimizing the Deep Neural Networks by Layer-Wise Refined Pruning and the Acceleration on FPGA

doi: 10.1155/2022/8039281

Figure Lengend Snippet: ResNet101 on ImageNet100.

Article Snippet: In this section, we deploy both the original and the pruned VGG13BN and ResNet101 trained on ImageNet100 on the Xilinx FPGA platform of Zynq UltraScale + MPSoC ZCU102 Evaluation Kit.

Techniques:

Journal: Computational Intelligence and Neuroscience

Article Title: Optimizing the Deep Neural Networks by Layer-Wise Refined Pruning and the Acceleration on FPGA

doi: 10.1155/2022/8039281

Figure Lengend Snippet: Accuracy comparison after quantization.

Article Snippet: In this section, we deploy both the original and the pruned VGG13BN and ResNet101 trained on ImageNet100 on the Xilinx FPGA platform of Zynq UltraScale + MPSoC ZCU102 Evaluation Kit.

Techniques: Comparison

Journal: Computational Intelligence and Neuroscience

Article Title: Optimizing the Deep Neural Networks by Layer-Wise Refined Pruning and the Acceleration on FPGA

doi: 10.1155/2022/8039281

Figure Lengend Snippet: Overall performance of xmodel on FPGA.

Article Snippet: In this section, we deploy both the original and the pruned VGG13BN and ResNet101 trained on ImageNet100 on the Xilinx FPGA platform of Zynq UltraScale + MPSoC ZCU102 Evaluation Kit.

Techniques:

Journal: Computational Intelligence and Neuroscience

Article Title: Optimizing the Deep Neural Networks by Layer-Wise Refined Pruning and the Acceleration on FPGA

doi: 10.1155/2022/8039281

Figure Lengend Snippet: ResNet101 subgraph-wise performance.

Article Snippet: In this section, we deploy both the original and the pruned VGG13BN and ResNet101 trained on ImageNet100 on the Xilinx FPGA platform of Zynq UltraScale + MPSoC ZCU102 Evaluation Kit.

Techniques:

Journal: Computational Intelligence and Neuroscience

Article Title: Gravitational Wave-Signal Recognition Model Based on Fourier Transform and Convolutional Neural Network

doi: 10.1155/2022/5892188

Figure Lengend Snippet: ResNet101 validation comparison.

Article Snippet: Additionally, the Resnet101 model, developed on the Baidu EasyDL platform, is adopted as a comparative model. Our average recognition accuracy performs approximately 4% better than the Resnet101 model. Based on the excellent performance of convolutional neural network in the field of image recognition, this paper studies the characteristics of gravitational wave signals and obtains a more appropriate recognition model after training and tuning, in order to achieve the purpose of automatic recognition of whether the signal data contain real gravitational wave signals.

Techniques: Biomarker Discovery, Comparison