TY - GEN
T1 - Invited Paper
T2 - 42nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2023
AU - Sui, Yang
AU - Zhu, Minning
AU - Huang, Lingyi
AU - Wu, Chung Tse Michael
AU - Yuan, Bo
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Radio Frequency Neural Networks (RFNNs) have demonstrated advantages in realizing intelligent applications across various domains. However, as the model size of deep neural networks rapidly increases, implementing large-scale RFNN in practice requires an extensive number of RF interferometers and consumes a substantial amount of energy. To address this challenge, we propose to utilize low-rank decomposition to transform a large-scale RFNN into a compact RFNN while almost preserving its accuracy. Specifically, we develop a Tensor-Train RFNN (TT-RFNN) where each layer comprises a sequence of low-rank third-order tensors, leading to a notable reduction in parameter count, thereby optimizing RF interferometer utilization in comparison to the original large-scale RFNN. Additionally, considering the inherent physical errors when mapping TT-RFNN to RF device parameters in real-world deployment, from a general perspective, we construct the Robust TT-RFNN (RTT-RFNN) by incorporating a robustness solver on TT-RFNN to enhance its robustness. To adapt the RTT-RFNN to varying requirements of reshaping operations, we further provide a reconfigurable reshaping solution employing RF switch matrices. Empirical evaluations conducted on MNIST and CIFAR-10 datasets show the effectiveness of our proposed method.
AB - Radio Frequency Neural Networks (RFNNs) have demonstrated advantages in realizing intelligent applications across various domains. However, as the model size of deep neural networks rapidly increases, implementing large-scale RFNN in practice requires an extensive number of RF interferometers and consumes a substantial amount of energy. To address this challenge, we propose to utilize low-rank decomposition to transform a large-scale RFNN into a compact RFNN while almost preserving its accuracy. Specifically, we develop a Tensor-Train RFNN (TT-RFNN) where each layer comprises a sequence of low-rank third-order tensors, leading to a notable reduction in parameter count, thereby optimizing RF interferometer utilization in comparison to the original large-scale RFNN. Additionally, considering the inherent physical errors when mapping TT-RFNN to RF device parameters in real-world deployment, from a general perspective, we construct the Robust TT-RFNN (RTT-RFNN) by incorporating a robustness solver on TT-RFNN to enhance its robustness. To adapt the RTT-RFNN to varying requirements of reshaping operations, we further provide a reconfigurable reshaping solution employing RF switch matrices. Empirical evaluations conducted on MNIST and CIFAR-10 datasets show the effectiveness of our proposed method.
KW - Radio frequency neural network
KW - efficiency
KW - model compression
KW - robustness
KW - tensor-train decomposition
UR - http://www.scopus.com/inward/record.url?scp=85181399114&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85181399114&partnerID=8YFLogxK
U2 - 10.1109/ICCAD57390.2023.10323823
DO - 10.1109/ICCAD57390.2023.10323823
M3 - Conference contribution
AN - SCOPUS:85181399114
T3 - IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
BT - 2023 42nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2023 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 28 October 2023 through 2 November 2023
ER -