Maryam Parsa, J. Parker Mitchell, Catherine D. Schuman, Robert M. Patton, Thomas E. Potok and Kaushik Roy

December, 2019

IEEE International Conference on Big Data

http://bigdataieee.org/BigData2019/

View Article

Abstract

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.

Citation Information

Text

author     M. Parsa and J. P. Mitchell and C. D. Schuman and R. M. Patton and T. E. Potok and K. Roy
title      Bayesian-Based Hyperparameter Optimization for Spiking Neuromorphic Systems
booktitle  IEEE International Conference on Big Data
month      December
year       2019
pages      4472-4478
location   Los Angeles, CA
where      http://neuromorphic.eecs.utk.edu/publications/2019-12-09-bayesian-based-hyperparameter-optimization-for-spiking-neuromorphic-systems

Bibtex

@INPROCEEDINGS{pms:19:bbh,
    author = "M. Parsa and J. P. Mitchell and C. D. Schuman and R. M. Patton and T. E. Potok and K. Roy",
    title = "Bayesian-Based Hyperparameter Optimization for Spiking Neuromorphic Systems",
    booktitle = "IEEE International Conference on Big Data",
    month = "December",
    year = "2019",
    pages = "4472-4478",
    location = "Los Angeles, CA",
    where = "http://neuromorphic.eecs.utk.edu/publications/2019-12-09-bayesian-based-hyperparameter-optimization-for-spiking-neuromorphic-systems"
}