Skip to main content

Hyperparameter Optimization in Binary Communication Networks for Neuromorphic Deployment...

Publication Type
Conference Paper
Book Title
2020 International Joint Conference on Neural Networks (IJCNN)
Publication Date
Page Numbers
1 to 9
Conference Name
International Joint Conference on Neural Networks (IJCNN)
Conference Location
Glasgow, Scotland
Conference Sponsor
Conference Date

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.