Accurate and Efficient Quantized Reservoir Computing System

Shiya Liu, Yibin Liang, Victor Gan, Lingjia Liu, Yang Yi
Virginia Tech


Quantization is a widely used technique to deploy deep learning models on embedded systems since this technique could reduce the model size and computation dramatically without losing much accuracy. Many quantization approaches have been proposed in recent years. Some quantization approaches are aggressive which could sufficiently reduce the model size and computation. However, the accuracy could be significantly decreased. To resolve this issue, some research groups have proposed smoother approaches to reduce accuracy loss. However, smoother approaches would use more resources than aggressive approaches. In our work, we proposed a quantization approach which reduces resource utilization dramatically without losing much accuracy. We have successfully applied our quantization approach to reservoir computing (RC) system. Compared to the RC system using floating-point numbers, our proposed RC system reduces the resource utilization of BRAM, DSP, Flip-Flop (FF) and Lookup Table (LUT) by 47%, 93%, 93%, and 87% respectively and only loses 0.08% accuracy on the NARMA10 dataset. Meanwhile, our proposed DFR computing system uses approximately 45%, 14%, and 21% less BRAM, FF, and LUT respectively than the quantized DFR computing system using another quantization approach.