Corpus ID: 212644764

Benchmarking TinyML Systems: Challenges and Direction

@article{Banbury2020BenchmarkingTS,
  title={Benchmarking TinyML Systems: Challenges and Direction},
  author={Colby R. Banbury and Vijay Janapa Reddi and Max Lam and William Fu and Amin Fazel and Jeremy Holleman and Xinyuan Huang and Robert Arana Hurtado and David E. Kanter and Anton Lokhmotov and David A. Patterson and Danilo Pau and Jae-sun Seo and Jeff Sieracki and Urmish Thakker and Marian Verhelst and Poonam Yadav},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.04821}
}
  • Colby R. Banbury, Vijay Janapa Reddi, +14 authors Poonam Yadav
  • Published 2020
  • Computer Science
  • ArXiv
  • Recent advancements in ultra-low-power machine learning (TinyML) hardware promises to unlock an entirely new class of smart applications. However, continued progress is limited by the lack of a widely accepted benchmark for these systems. Benchmarking allows us to measure and thereby systematically compare, evaluate, and improve the performance of systems. In this position paper, we present the current landscape of TinyML and discuss the challenges and direction towards developing a fair and… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 24 REFERENCES

    MLPerf Inference Benchmark

    VIEW 1 EXCERPT

    HAQ: Hardware-Aware Automated Quantization With Mixed Precision

    Hello Edge: Keyword Spotting on Microcontrollers

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    GAP-8: A RISC-V SoC for AI at the Edge of the IoT

    • Eric Flamand, Davide Rossi, +4 authors Luca Benini
    • Computer Science
    • 2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP)
    • 2018

    A Low Power, Fully Event-Based Gesture Recognition System