Scalable and modularized RTL compilation of Convolutional Neural Networks onto FPGA

Mathematics

• Field Programmable Gate Array 100%
• Compilation 82%
• Neural Networks 59%
• High-level Synthesis 50%
• Throughput 49%
• Compiler 33%
• Neural Network Model 31%
• Hardware 31%
• Design 23%
• System Architecture 21%
• Resource Constraints 19%
• Network Structure 16%
• Large Data 16%
• Learning Algorithm 15%
• Parallelism 14%
• Accelerate 13%
• Integrate 13%
• Optimise 13%
• Flexibility 12%
• Maximise 11%
• Resources 11%
• Learning 11%
• Optimization 9%
• Methodology 9%
• Strategy 8%
• Module 8%
• Computing 7%
• Hardware Acceleration 2%

Engineering & Materials Science

• Convolutional neural networks 57%
• Field programmable gate arrays (FPGA) 51%
• High level synthesis 32%
• Throughput 26%
• Deep learning 22%
• Computer hardware 22%
• Learning algorithms 10%
• Data storage equipment 7%