Sparse convolutional neural network acceleration with lossless input feature map compression for resource-constrained systems

Computer Science

• Convolutional Neural Network 100%
• Hardware Accelerator 40%
• Convolutional Layer 40%
• Sparsity 40%
• Field Programmable Gate Arrays 40%
• Network Inference 40%
• Participatory Design 20%
• Power Consumption 20%
• Energy Consumption 20%
• Main Memory 20%
• Optimization Technique 20%
• Hardware Resource 20%
• Data Compression 20%
• Compressed Data 20%
• Design Optimization 20%
• Research Effort 20%
• Data Type 20%
• System-on-Chip 20%
• Lossless Compression 20%
• Compression Scheme 20%