TY - GEN
T1 - Printed Stochastic Computing Neural Networks
AU - Weller, Dennis D.
AU - Bleier, Nathaniel
AU - Hefenbrock, Michael
AU - Aghassi-Hagmann, Jasmin
AU - Beigl, Michael
AU - Kumar, Rakesh
AU - Tahoori, Mehdi B.
N1 - Funding Information:
Kumar would like to thank NSF for partial support of this work.
Publisher Copyright:
© 2021 EDAA.
PY - 2021/2/1
Y1 - 2021/2/1
N2 - Printed electronics (PE) offers flexible, extremely low-cost, and on-demand hardware due to its additive manufacturing process, enabling emerging ultra-low-cost applications, including machine learning applications. However, large feature sizes in PE limit the complexity of a machine learning classifier (e.g., a neural network (NN)) in PE. Stochastic computing Neural Networks (SC-NNs) can reduce area in silicon technologies, but still require complex designs due to unique implementation tradeoffs in PE. In this paper, we propose a printed mixed-signal system, which substitutes complex and power-hungry conventional stochastic computing (SC) components by printed analog designs. The printed mixed-signal SC consumes only 35% of power consumption and requires only 25% of area compared to a conventional 4-bit NN implementation. We also show that the proposed mixed-signal SC-NN provides good accuracy for popular neural network classification problems. We consider this work as an important step towards the realization of printed SC-NN hardware for near-sensor-processing.
AB - Printed electronics (PE) offers flexible, extremely low-cost, and on-demand hardware due to its additive manufacturing process, enabling emerging ultra-low-cost applications, including machine learning applications. However, large feature sizes in PE limit the complexity of a machine learning classifier (e.g., a neural network (NN)) in PE. Stochastic computing Neural Networks (SC-NNs) can reduce area in silicon technologies, but still require complex designs due to unique implementation tradeoffs in PE. In this paper, we propose a printed mixed-signal system, which substitutes complex and power-hungry conventional stochastic computing (SC) components by printed analog designs. The printed mixed-signal SC consumes only 35% of power consumption and requires only 25% of area compared to a conventional 4-bit NN implementation. We also show that the proposed mixed-signal SC-NN provides good accuracy for popular neural network classification problems. We consider this work as an important step towards the realization of printed SC-NN hardware for near-sensor-processing.
KW - electrolyte-gated transistors
KW - neural networks
KW - printed electronics
KW - stochastic computing
UR - http://www.scopus.com/inward/record.url?scp=85111040463&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85111040463&partnerID=8YFLogxK
U2 - 10.23919/DATE51398.2021.9474254
DO - 10.23919/DATE51398.2021.9474254
M3 - Conference contribution
AN - SCOPUS:85111040463
T3 - Proceedings -Design, Automation and Test in Europe, DATE
SP - 914
EP - 919
BT - Proceedings of the 2021 Design, Automation and Test in Europe, DATE 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 Design, Automation and Test in Europe Conference and Exhibition, DATE 2021
Y2 - 1 February 2021 through 5 February 2021
ER -