TY - GEN
T1 - Bayesian-based Hyperparameter Optimization for Spiking Neuromorphic Systems
AU - Parsa, Maryam
AU - Mitchell, J. Parker
AU - Schuman, Catherine D.
AU - Patton, Robert M.
AU - Potok, Thomas E.
AU - Roy, Kaushik
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - Designing a neuromorphic computing system involves selection of several hyperparameters that not only affect the accuracy of the framework, but also the energy efficiency and speed of inference and training. These hyperparameters might be inherent to the training of the spiking neural network (SNN), the input/output encoding of the real-world data to spikes, or the underlying neuromorphic hardware. In this work, we present a Bayesian-based hyperparameter optimization approach for spiking neuromorphic systems, and we show how this optimization framework can lead to significant improvement in designing accurate neuromorphic computing systems. In particular, we show that this hyperparameter optimization approach can discover the same optimal hyperparameter set for input encoding as a grid search, but with far fewer evaluations and far less time. We also show the impact of hardware-specific hyperparameters on the performance of the system, and we demonstrate that by optimizing these hyperparameters, we can achieve significantly better application performance.
AB - Designing a neuromorphic computing system involves selection of several hyperparameters that not only affect the accuracy of the framework, but also the energy efficiency and speed of inference and training. These hyperparameters might be inherent to the training of the spiking neural network (SNN), the input/output encoding of the real-world data to spikes, or the underlying neuromorphic hardware. In this work, we present a Bayesian-based hyperparameter optimization approach for spiking neuromorphic systems, and we show how this optimization framework can lead to significant improvement in designing accurate neuromorphic computing systems. In particular, we show that this hyperparameter optimization approach can discover the same optimal hyperparameter set for input encoding as a grid search, but with far fewer evaluations and far less time. We also show the impact of hardware-specific hyperparameters on the performance of the system, and we demonstrate that by optimizing these hyperparameters, we can achieve significantly better application performance.
KW - Accurate and Energy Efficient Machine Learning
KW - Hyperparameter Optimization
KW - Spiking Neuromorphic Computing
UR - http://www.scopus.com/inward/record.url?scp=85081372514&partnerID=8YFLogxK
U2 - 10.1109/BigData47090.2019.9006383
DO - 10.1109/BigData47090.2019.9006383
M3 - Conference contribution
AN - SCOPUS:85081372514
T3 - Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019
SP - 4472
EP - 4478
BT - Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019
A2 - Baru, Chaitanya
A2 - Huan, Jun
A2 - Khan, Latifur
A2 - Hu, Xiaohua Tony
A2 - Ak, Ronay
A2 - Tian, Yuanyuan
A2 - Barga, Roger
A2 - Zaniolo, Carlo
A2 - Lee, Kisung
A2 - Ye, Yanfang Fanny
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Conference on Big Data, Big Data 2019
Y2 - 9 December 2019 through 12 December 2019
ER -
