Papers
Topics
Authors
Recent
Search
2000 character limit reached

On-sensor Printed Machine Learning Classification via Bespoke ADC and Decision Tree Co-Design

Published 2 Dec 2023 in cs.LG | (2312.01172v1)

Abstract: Printed electronics (PE) technology provides cost-effective hardware with unmet customization, due to their low non-recurring engineering and fabrication costs. PE exhibit features such as flexibility, stretchability, porosity, and conformality, which make them a prominent candidate for enabling ubiquitous computing. Still, the large feature sizes in PE limit the realization of complex printed circuits, such as machine learning classifiers, especially when processing sensor inputs is necessary, mainly due to the costly analog-to-digital converters (ADCs). To this end, we propose the design of fully customized ADCs and present, for the first time, a co-design framework for generating bespoke Decision Tree classifiers. Our comprehensive evaluation shows that our co-design enables self-powered operation of on-sensor printed classifiers in all benchmark cases.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (17)
  1. N. Bleier, M. Mubarik, F. Rasheed, J. Aghassi-Hagmann, M. B. Tahoori, and R. Kumar, “Printed microprocessors,” in Annu. Int. Symp. Computer Architecture (ISCA), jun 2020, pp. 213–226.
  2. M. H. Mubarik et al., “Printed machine learning classifiers,” in Annu. Int. Symp. Microarchitecture (MICRO), 2020, pp. 73–87.
  3. G. Armeniakos, G. Zervakis, D. Soudris, M. B. Tahoori, and J. Henkel, “Co-design of approximate multilayer perceptron for ultra-resource constrained printed circuits,” IEEE Trans. Comput., pp. 1–8, 2023.
  4. G. Armeniakos, G. Zervakis, D. Soudris, M. B. Tahoori, and J. Henkel, “Model-to-circuit cross-approximation for printed machine learning classifiers,” IEEE Trans. Comput.-Aided Design Integr. Circuits Syst., 2023.
  5. A. Kokkinis et al., “Hardware-aware automated neural minimization for printed multilayer perceptrons,” in Design, Automation & Test in Europe Conference & Exhibition (DATE), 2023, pp. 1–2.
  6. D. D. Weller et al., “Printed stochastic computing neural networks,” in Design, Automation & Test in Europe Conference & Exhibition (DATE), 2021, pp. 914–919.
  7. K. Balaskas et al., “Approximate decision trees for machine learning classification on tiny printed circuits,” in Int. Symp. Quality Electronic Design, 2022, pp. 1–6.
  8. M. Shafique, R. Hafiz, S. Rehman, W. El-Harouni, and J. Henkel, “Cross-layer approximate computing: From logic to architectures,” in Design Automation Conference (DAC), 2016, pp. 1–6.
  9. A. Ren et al., “Sc-dcnn: Highly-scalable deep convolutional neural network using stochastic computing,” in Int. Conf. Architectural Support for Programming Languages and Operating Systems, 2017, p. 405–418.
  10. D. Wu, J. Li, R. Yin, H. Hsiao, Y. Kim, and J. S. Miguel, “Ugemm: Unary computing architecture for gemm applications,” in Int. Symp. Computer Architecture (ISCA), 2020, pp. 377–390.
  11. J. Henkel et al., “Approximate computing and the efficient machine learning expedition,” in Int. Conf. Computer Aided Design, 2022.
  12. G. Tzimpragos, A. Madhavan, D. Vasudevan, D. Strukov, and T. Sherwood, “Boosted race trees for low energy classification,” in Int. Conf. Architectural Support for Programming Languages and Operating Systems, ser. ASPLOS ’19, 2019, p. 215–228.
  13. M. H. Najafi, D. J. Lilja, M. D. Riedel, and K. Bazargan, “Low-cost sorting network circuits using unary processing,” IEEE Trans. VLSI Syst., vol. 26, no. 8, pp. 1471–1480, 2018.
  14. A. Khataei, G. Singh, and K. Bazargan, “Approximate hybrid binary-unary computing with applications in bert language model and image processing,” in Int. Symp. Field Programmable Gate Arrays (FPGA), 2023, p. 165–175.
  15. M. Jaworski, P. Duda, and L. Rutkowski, “New splitting criteria for decision trees in stationary data streams,” IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 6, pp. 2516–2529, 2018.
  16. K. N. Markelle Kelly, Rachel Longjohn, “The uci machine learning repository.” [Online]. Available: https://archive.ics.uci.edu
  17. A. Ahmed et al., “Additively manufactured nano-mechanical energy harvesting systems: advancements, potential applications, challenges and future perspectives,” Nano Convergence, vol. 8, no. 37, 2021.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up