Search NASA⌕ Search

DOE OSTI · 1671416

Hyperparameter Optimization in Binary Communication Networks for Neuromorphic Deployment

Also available from

Abstract

Training neural networks for neuromorphic deployment is non-trivial. There have been a variety of approaches proposed to adapt back-propagation or back-propagation-like algorithms appropriate for training. Considering that these networks often have very different performance characteristics than traditional neural networks, it is often unclear how to set either the network topology or the hyperparameters to achieve optimal performance. In this work, we introduce a Bayesian approach for optimizing the hyperparameters of an algorithm for training binary communication networks that can be deployed to neuromorphic hardware. We show that by optimizing the hyperparameters on this algorithm for each dataset, we can achieve improvements in accuracy over the previous state-of-the-art for this algorithm on each dataset (by up to 15 percent). This jump in performance continues to emphasize the potential when converting traditional neural networks to binary communication applicable to neuromorphic hardware.

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Parsa, Maryam, Schuman, Catherine, Date, Prasanna, Rose, Derek, Kay, Bill, Mitchell, Parker, Young, Steven, Dellana, Ryan, Severa, William, Potok, Thomas, Roy, Kaushik. 2020-07-01. Hyperparameter Optimization in Binary Communication Networks for Neuromorphic Deployment. https://doi.org/10.1109/ijcnn48605.2020.9206872. https://searchnasa.com/record/osti%3A1671416/hyperparameter-optimization-in-binary-communication-networks-for-neuromorphic-deployment

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.